Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1230. Min Range: -8.1230
Max Act: 8.1230. Min Act: -0.1700
Data Index: 7689940 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1230. Min Range: -8.1230
Max Act: 8.0605. Min Act: -0.1700
Data Index: 1834671 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.9980. Min Act: -0.1700
Data Index: 3205959 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.8105. Min Act: -0.1700
Data Index: 3807131 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.8105. Min Act: -0.1700
Data Index: 7422450 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.8417. Min Act: -0.1700
Data Index: 7689947 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.8105. Min Act: -0.1700
Data Index: 2917989 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.8105. Min Act: -0.1700
Data Index: 2437678 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.7792. Min Act: -0.1700
Data Index: 8466613 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.7480. Min Act: -0.1700
Data Index: 5360415 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.7167. Min Act: -0.1700
Data Index: 4740745 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.6855. Min Act: -0.1700
Data Index: 7689948 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.6855. Min Act: -0.1700
Data Index: 8429075 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.6855. Min Act: -0.1690
Data Index: 3800990 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.6542. Min Act: -0.1700
Data Index: 3846296 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.6230. Min Act: -0.1700
Data Index: 3970028 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.6230. Min Act: -0.1700
Data Index: 7428323 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.5917. Min Act: -0.1700
Data Index: 6846772 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.5917. Min Act: -0.1700
Data Index: 2487785 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1230. Min Range: -8.1230
Max Act: 7.5605. Min Act: -0.1700
Data Index: 2117592 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19