Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.1958. Min Act: -0.1700
Data Index: 2202048 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.1333. Min Act: -0.1700
Data Index: 2563797 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.1645. Min Act: -0.1700
Data Index: 1078334 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8833. Min Act: -0.1700
Data Index: 5184069 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8520. Min Act: -0.1700
Data Index: 8828985 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6645. Min Act: -0.1700
Data Index: 2656168 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6020. Min Act: -0.1700
Data Index: 368902 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.5395. Min Act: -0.1700
Data Index: 1045310 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.5708. Min Act: -0.1700
Data Index: 5866915 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.5083. Min Act: -0.1700
Data Index: 187067 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4770. Min Act: -0.1700
Data Index: 4327641 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4458. Min Act: -0.1700
Data Index: 7578574 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4458. Min Act: -0.1700
Data Index: 667784 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4145. Min Act: -0.1700
Data Index: 2015288 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3520. Min Act: -0.1700
Data Index: 5849906 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3520. Min Act: -0.1700
Data Index: 4765706 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3520. Min Act: -0.1700
Data Index: 8440674 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3520. Min Act: -0.1700
Data Index: 5344687 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3208. Min Act: -0.1700
Data Index: 4749560 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.2895. Min Act: -0.1700
Data Index: 2271494 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19