Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.6395. Min Act: -0.1700
Data Index: 8140580 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 6232620 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 2453093 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 1671041 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 8662380 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3895. Min Act: -0.1700
Data Index: 4384400 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3583. Min Act: -0.1700
Data Index: 3028700 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3895. Min Act: -0.1700
Data Index: 827462 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2958. Min Act: -0.1700
Data Index: 2949141 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3583. Min Act: -0.1700
Data Index: 5816623 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3270. Min Act: -0.1700
Data Index: 220300 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2958. Min Act: -0.1700
Data Index: 7681484 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2958. Min Act: -0.1700
Data Index: 3218403 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2958. Min Act: -0.1700
Data Index: 6346531 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2645. Min Act: -0.1699
Data Index: 5604737 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2645. Min Act: -0.1700
Data Index: 5553226 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2645. Min Act: -0.1700
Data Index: 1813093 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2645. Min Act: -0.1700
Data Index: 6957677 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2333. Min Act: -0.1700
Data Index: 4788130 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2333. Min Act: -0.1700
Data Index: 185751 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19