Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 780 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.3418. Min Act: -0.1700
Data Index: 8042955 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 5436978 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 8780160 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 5018728 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 2101011 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2168. Min Act: -0.1700
Data Index: 6997144 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 718704 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 5851323 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 6738408 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2168. Min Act: -0.1700
Data Index: 2340297 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1856. Min Act: -0.1700
Data Index: 8258413 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2481. Min Act: -0.1700
Data Index: 4178522 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.2168. Min Act: -0.1700
Data Index: 334056 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1543. Min Act: -0.1700
Data Index: 3036815 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1543. Min Act: -0.1700
Data Index: 3972512 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1856. Min Act: -0.1700
Data Index: 1629914 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1856. Min Act: -0.1700
Data Index: 1332886 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1231. Min Act: -0.1700
Data Index: 5906283 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1231. Min Act: -0.1700
Data Index: 7326463 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3418. Min Range: -4.3418
Max Act: 4.1543. Min Act: -0.1700
Data Index: 5332096 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19