Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2064 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.3565. Min Act: -0.1700
Data Index: 8757443 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.2315. Min Act: -0.1700
Data Index: 8490906 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.2315. Min Act: -0.1700
Data Index: 2337028 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.2002. Min Act: -0.1700
Data Index: 7946503 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.1689. Min Act: -0.1700
Data Index: 2537169 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.1689. Min Act: -0.1700
Data Index: 2911206 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.1689. Min Act: -0.1700
Data Index: 7154965 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.1377. Min Act: -0.1700
Data Index: 5082691 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0752. Min Act: -0.1700
Data Index: 8214993 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.1064. Min Act: -0.1700
Data Index: 378340 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0752. Min Act: -0.1700
Data Index: 3279091 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0752. Min Act: -0.1700
Data Index: 1244580 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0439. Min Act: -0.1700
Data Index: 6041092 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0752. Min Act: -0.1700
Data Index: 492509 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0127. Min Act: -0.1700
Data Index: 5730330 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0439. Min Act: -0.1700
Data Index: 3590883 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3565. Min Range: -4.3565
Max Act: 3.9814. Min Act: -0.1700
Data Index: 87713 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3565. Min Range: -4.3565
Max Act: 4.0127. Min Act: -0.1700
Data Index: 5526154 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3565. Min Range: -4.3565
Max Act: 3.9814. Min Act: -0.1700
Data Index: 3819191 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3565. Min Range: -4.3565
Max Act: 3.9501. Min Act: -0.1700
Data Index: 752364 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19