Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.9166. Min Act: -0.1700
Data Index: 8451282 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.7603. Min Act: -0.1700
Data Index: 4794937 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.6666. Min Act: -0.1700
Data Index: 6227474 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.6041. Min Act: -0.1700
Data Index: 2584398 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.5416. Min Act: -0.1700
Data Index: 212385 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.5103. Min Act: -0.1700
Data Index: 6120110 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4478. Min Act: -0.1700
Data Index: 5985652 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4478. Min Act: -0.1700
Data Index: 728168 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4478. Min Act: -0.1700
Data Index: 5290504 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4166. Min Act: -0.1700
Data Index: 4942576 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4166. Min Act: -0.1700
Data Index: 7005660 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4166. Min Act: -0.1700
Data Index: 7031987 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4166. Min Act: -0.1700
Data Index: 2660731 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.4166. Min Act: -0.1700
Data Index: 6102096 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.3853. Min Act: -0.1700
Data Index: 718013 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.3853. Min Act: -0.1700
Data Index: 502591 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.3853. Min Act: -0.1700
Data Index: 5961065 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.3853. Min Act: -0.1700
Data Index: 7575566 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.3853. Min Act: -0.1700
Data Index: 382807 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9166. Min Range: -5.9166
Max Act: 5.3853. Min Act: -0.1700
Data Index: 3102576 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19