Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6908. Min Act: -0.1699
Data Index: 6638040 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6908. Min Act: -0.1700
Data Index: 6760117 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6908. Min Act: -0.1700
Data Index: 5292836 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6596. Min Act: -0.1700
Data Index: 895828 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6596. Min Act: -0.1700
Data Index: 2429947 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6596. Min Act: -0.1700
Data Index: 6683525 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6596. Min Act: -0.1700
Data Index: 653667 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6596. Min Act: -0.1700
Data Index: 5151466 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6596. Min Act: -0.1700
Data Index: 8760555 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5971. Min Act: -0.1699
Data Index: 1160460 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6283. Min Act: -0.1700
Data Index: 8325422 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6283. Min Act: -0.1700
Data Index: 7607209 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5971. Min Act: -0.1700
Data Index: 4386316 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5971. Min Act: -0.1700
Data Index: 5421336 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5658. Min Act: -0.1700
Data Index: 7115855 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5658. Min Act: -0.1700
Data Index: 3303756 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.6283. Min Act: -0.1700
Data Index: 2558399 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5658. Min Act: -0.1700
Data Index: 6102174 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5658. Min Act: -0.1700
Data Index: 6298739 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6908. Min Range: -6.6908
Max Act: 6.5658. Min Act: -0.1700
Data Index: 7068739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19