Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.1976. Min Act: -0.1700
Data Index: 4118406 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.1663. Min Act: -0.1700
Data Index: 8445134 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.1038. Min Act: -0.1700
Data Index: 3100541 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.1351. Min Act: -0.1700
Data Index: 2769422 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.1038. Min Act: -0.1700
Data Index: 7210708 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.0726. Min Act: -0.1700
Data Index: 284702 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1976. Min Range: -5.1976
Max Act: 5.0413. Min Act: -0.1700
Data Index: 6755507 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9788. Min Act: -0.1700
Data Index: 2896271 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9476. Min Act: -0.1700
Data Index: 4050476 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9163. Min Act: -0.1700
Data Index: 1269678 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9476. Min Act: -0.1700
Data Index: 5040632 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9476. Min Act: -0.1700
Data Index: 48012 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9476. Min Act: -0.1700
Data Index: 5284152 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9163. Min Act: -0.1700
Data Index: 7334561 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.9163. Min Act: -0.1700
Data Index: 6650991 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.8851. Min Act: -0.1700
Data Index: 6843058 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.8851. Min Act: -0.1700
Data Index: 7837931 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.8851. Min Act: -0.1700
Data Index: 929837 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.8538. Min Act: -0.1700
Data Index: 1415300 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1976. Min Range: -5.1976
Max Act: 4.8538. Min Act: -0.1700
Data Index: 4039002 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19