Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1448. Min Range: -6.1448
Max Act: 6.1448. Min Act: -0.1700
Data Index: 1319449 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1448. Min Range: -6.1448
Max Act: 6.1135. Min Act: -0.1700
Data Index: 5132063 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1448. Min Range: -6.1448
Max Act: 6.0823. Min Act: -0.1700
Data Index: 7898457 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1448. Min Range: -6.1448
Max Act: 6.0510. Min Act: -0.1700
Data Index: 5341637 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1448. Min Range: -6.1448
Max Act: 6.0198. Min Act: -0.1700
Data Index: 2533728 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1448. Min Range: -6.1448
Max Act: 6.0198. Min Act: -0.1700
Data Index: 7971425 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9885. Min Act: -0.1700
Data Index: 4731523 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9885. Min Act: -0.1700
Data Index: 6192538 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9885. Min Act: -0.1700
Data Index: 5995357 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9885. Min Act: -0.1700
Data Index: 2813166 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9573. Min Act: -0.1700
Data Index: 7787887 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9573. Min Act: -0.1700
Data Index: 5978017 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9885. Min Act: -0.1700
Data Index: 2330632 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9260. Min Act: -0.1700
Data Index: 5654653 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9260. Min Act: -0.1700
Data Index: 2796052 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9260. Min Act: -0.1700
Data Index: 3329302 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9260. Min Act: -0.1700
Data Index: 1894914 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9260. Min Act: -0.1700
Data Index: 4245728 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.8948. Min Act: -0.1700
Data Index: 7323463 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1448. Min Range: -6.1448
Max Act: 5.9260. Min Act: -0.1700
Data Index: 7801115 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19