Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5411 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.6304. Min Act: -0.1700
Data Index: 1119065 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5679. Min Act: -0.1700
Data Index: 7022169 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5054. Min Act: -0.1700
Data Index: 8707318 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.5054. Min Act: -0.1700
Data Index: 3160347 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4741. Min Act: -0.1700
Data Index: 1383978 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4429. Min Act: -0.1700
Data Index: 5554982 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 4270279 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 5740981 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 7434417 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 5553518 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6360798 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3179. Min Act: -0.1700
Data Index: 3297359 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3179. Min Act: -0.1700
Data Index: 6112495 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3368584 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2866. Min Act: -0.1700
Data Index: 4066532 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2866. Min Act: -0.1700
Data Index: 5312481 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2241. Min Act: -0.1700
Data Index: 5852607 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2241. Min Act: -0.1700
Data Index: 4586006 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.1929. Min Act: -0.1700
Data Index: 7233037 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2241. Min Act: -0.1700
Data Index: 6576612 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19