Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.9284. Min Act: -0.1700
Data Index: 1148302 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.8034. Min Act: -0.1700
Data Index: 3466108 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.8034. Min Act: -0.1700
Data Index: 4644558 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.8034. Min Act: -0.1700
Data Index: 6405143 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.7097. Min Act: -0.1700
Data Index: 1050218 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.7097. Min Act: -0.1700
Data Index: 6493442 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.5847. Min Act: -0.1700
Data Index: 5699288 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.6159. Min Act: -0.1700
Data Index: 4496703 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.5847. Min Act: -0.1700
Data Index: 8711357 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.5534. Min Act: -0.1700
Data Index: 7547536 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.5222. Min Act: -0.1700
Data Index: 4603484 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.5222. Min Act: -0.1700
Data Index: 3678485 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.4909. Min Act: -0.1700
Data Index: 363605 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.4597. Min Act: -0.1700
Data Index: 5994096 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.4284. Min Act: -0.1700
Data Index: 8579883 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.4284. Min Act: -0.1700
Data Index: 4451938 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.4284. Min Act: -0.1700
Data Index: 5068279 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.4284. Min Act: -0.1700
Data Index: 4547494 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.3659. Min Act: -0.1700
Data Index: 5695422 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9284. Min Range: -7.9284
Max Act: 7.3972. Min Act: -0.1700
Data Index: 7441444 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19