Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4397 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2049. Min Range: -6.2049
Max Act: 6.2049. Min Act: -0.1700
Data Index: 1187439 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2049. Min Range: -6.2049
Max Act: 6.1112. Min Act: -0.1700
Data Index: 8403756 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.9862. Min Act: -0.1700
Data Index: 3863916 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2049. Min Range: -6.2049
Max Act: 6.0174. Min Act: -0.1700
Data Index: 582403 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.8924. Min Act: -0.1700
Data Index: 3867212 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.8924. Min Act: -0.1700
Data Index: 7817350 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4784391 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.8612. Min Act: -0.1700
Data Index: 1289338 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.8299. Min Act: -0.1700
Data Index: 2923502 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.8299. Min Act: -0.1700
Data Index: 2425708 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.7049. Min Act: -0.1700
Data Index: 4902910 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.7362. Min Act: -0.1700
Data Index: 4902911 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6737. Min Act: -0.1700
Data Index: 2344503 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6498313 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.7049. Min Act: -0.1700
Data Index: 5156781 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6737. Min Act: -0.1700
Data Index: 330371 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6654613 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6887205 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6112. Min Act: -0.1700
Data Index: 5868203 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2049. Min Range: -6.2049
Max Act: 5.6112. Min Act: -0.1700
Data Index: 1625787 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19