Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1239. Min Range: -5.1239
Max Act: 5.1239. Min Act: -0.1700
Data Index: 1366822 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1239. Min Range: -5.1239
Max Act: 5.0927. Min Act: -0.1700
Data Index: 6035781 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1239. Min Range: -5.1239
Max Act: 5.0302. Min Act: -0.1700
Data Index: 5102707 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1239. Min Range: -5.1239
Max Act: 5.0302. Min Act: -0.1700
Data Index: 3096541 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1239. Min Range: -5.1239
Max Act: 5.0302. Min Act: -0.1700
Data Index: 5752245 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.9989. Min Act: -0.1700
Data Index: 5761151 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3800613 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8739. Min Act: -0.1700
Data Index: 4044188 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8739. Min Act: -0.1700
Data Index: 6711083 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8427. Min Act: -0.1700
Data Index: 2879517 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8427. Min Act: -0.1700
Data Index: 5481974 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8114. Min Act: -0.1700
Data Index: 8088290 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8114. Min Act: -0.1700
Data Index: 2819444 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.8114. Min Act: -0.1700
Data Index: 5091878 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.7802. Min Act: -0.1700
Data Index: 8807473 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.7177. Min Act: -0.1700
Data Index: 3761689 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.7802. Min Act: -0.1700
Data Index: 5714417 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.7489. Min Act: -0.1700
Data Index: 1249423 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.7489. Min Act: -0.1700
Data Index: 6613906 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1239. Min Range: -5.1239
Max Act: 4.7489. Min Act: -0.1700
Data Index: 3310233 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19