Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5154 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2364. Min Range: -4.2364
Max Act: 4.2364. Min Act: -0.1700
Data Index: 1126647 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2364. Min Range: -4.2364
Max Act: 4.1114. Min Act: -0.1700
Data Index: 3092074 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2364. Min Range: -4.2364
Max Act: 4.0801. Min Act: -0.1700
Data Index: 6043973 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2364. Min Range: -4.2364
Max Act: 4.0489. Min Act: -0.1700
Data Index: 562458 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2364. Min Range: -4.2364
Max Act: 4.0176. Min Act: -0.1700
Data Index: 4089102 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2364. Min Range: -4.2364
Max Act: 4.0176. Min Act: -0.1700
Data Index: 5625588 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9863. Min Act: -0.1700
Data Index: 8455139 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9863. Min Act: -0.1700
Data Index: 3208188 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9551. Min Act: -0.1700
Data Index: 6582588 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9551. Min Act: -0.1700
Data Index: 5634717 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9551. Min Act: -0.1700
Data Index: 2041567 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9551. Min Act: -0.1700
Data Index: 428635 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9551. Min Act: -0.1700
Data Index: 5743258 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1431305 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9238. Min Act: -0.1700
Data Index: 5896793 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9238. Min Act: -0.1700
Data Index: 8482601 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.9238. Min Act: -0.1700
Data Index: 7672969 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.8925. Min Act: -0.1700
Data Index: 2299255 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.8925. Min Act: -0.1700
Data Index: 3429072 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2364. Min Range: -4.2364
Max Act: 3.8925. Min Act: -0.1700
Data Index: 3113701 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19