Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.3644. Min Range: -11.3644
Max Act: 11.3644. Min Act: -0.1700
Data Index: 4728523 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3644. Min Range: -11.3644
Max Act: 11.3019. Min Act: -0.1700
Data Index: 239351 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3644. Min Range: -11.3644
Max Act: 11.2394. Min Act: -0.1700
Data Index: 2814820 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.8019. Min Act: -0.1700
Data Index: 604863 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.7394. Min Act: -0.1700
Data Index: 2794493 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.8019. Min Act: -0.1700
Data Index: 3605816 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.6769. Min Act: -0.1700
Data Index: 4966395 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.6144. Min Act: -0.1700
Data Index: 4580544 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.6144. Min Act: -0.1700
Data Index: 5127160 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.6144. Min Act: -0.1700
Data Index: 2985517 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.6769. Min Act: -0.1700
Data Index: 295412 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.5519. Min Act: -0.1700
Data Index: 6277536 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.5519. Min Act: -0.1700
Data Index: 4111652 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.5519. Min Act: -0.1700
Data Index: 8189515 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.4894. Min Act: -0.1700
Data Index: 296408 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.4269. Min Act: -0.1700
Data Index: 644081 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.4269. Min Act: -0.1700
Data Index: 6164458 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.4269. Min Act: -0.1700
Data Index: 2281541 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.3644. Min Act: -0.1700
Data Index: 1237007 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3644. Min Range: -11.3644
Max Act: 10.3644. Min Act: -0.1700
Data Index: 5472829 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19