Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.5689. Min Act: -0.1700
Data Index: 188426 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.5377. Min Act: -0.1700
Data Index: 1283979 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.5377. Min Act: -0.1700
Data Index: 6474362 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.5064. Min Act: -0.1700
Data Index: 6452408 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.4752. Min Act: -0.1700
Data Index: 606275 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.4439. Min Act: -0.1700
Data Index: 2373695 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.4439. Min Act: -0.1700
Data Index: 7482020 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.3502. Min Act: -0.1700
Data Index: 1179123 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.3502. Min Act: -0.1700
Data Index: 7809401 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2877. Min Act: -0.1700
Data Index: 7541920 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.3189. Min Act: -0.1700
Data Index: 667885 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2877. Min Act: -0.1700
Data Index: 4741443 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2877. Min Act: -0.1700
Data Index: 4542099 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2877. Min Act: -0.1700
Data Index: 8472901 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2564. Min Act: -0.1700
Data Index: 4817313 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2564. Min Act: -0.1700
Data Index: 186169 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2252. Min Act: -0.1700
Data Index: 6156687 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2252. Min Act: -0.1700
Data Index: 1208645 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2252. Min Act: -0.1700
Data Index: 3413098 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5689. Min Range: -5.5689
Max Act: 5.2252. Min Act: -0.1700
Data Index: 7875210 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19