Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 479 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.6981. Min Act: -0.1700
Data Index: 6850973 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.6668. Min Act: -0.1700
Data Index: 2849546 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.6042. Min Act: -0.1700
Data Index: 6687439 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.5729. Min Act: -0.1700
Data Index: 1439245 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.5103. Min Act: -0.1700
Data Index: 209269 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4789. Min Act: -0.1700
Data Index: 7211492 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7288277 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4946. Min Act: -0.1700
Data Index: 2499074 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4946. Min Act: -0.1700
Data Index: 7228189 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4946. Min Act: -0.1700
Data Index: 3627812 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4633. Min Act: -0.1700
Data Index: 8396455 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4633. Min Act: -0.1700
Data Index: 8804226 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4476. Min Act: -0.1700
Data Index: 2324254 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4789. Min Act: -0.1700
Data Index: 488215 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4319. Min Act: -0.1700
Data Index: 4696421 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4162. Min Act: -0.1700
Data Index: 949566 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4476. Min Act: -0.1700
Data Index: 7999337 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4319. Min Act: -0.1700
Data Index: 252332 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4006. Min Act: -0.1700
Data Index: 6225156 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6981. Min Range: -3.6981
Max Act: 3.4162. Min Act: -0.1700
Data Index: 3998716 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19