Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.1844. Min Act: -0.1700
Data Index: 6425252 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.1530. Min Act: -0.1700
Data Index: 3030287 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.1057. Min Act: -0.1700
Data Index: 7292200 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.1057. Min Act: -0.1700
Data Index: 350867 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0742. Min Act: -0.1700
Data Index: 3152516 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0584. Min Act: -0.1700
Data Index: 2364624 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0426. Min Act: -0.1700
Data Index: 980066 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0426. Min Act: -0.1700
Data Index: 1041272 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0426. Min Act: -0.1700
Data Index: 1722190 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0268. Min Act: -0.1700
Data Index: 2543478 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0268. Min Act: -0.1700
Data Index: 5574438 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1844. Min Range: -3.1844
Max Act: 3.0110. Min Act: -0.1700
Data Index: 6954556 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9478. Min Act: -0.1700
Data Index: 215100 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9794. Min Act: -0.1700
Data Index: 3320050 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9952. Min Act: -0.1700
Data Index: 750276 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9794. Min Act: -0.1700
Data Index: 407390 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9478. Min Act: -0.1700
Data Index: 5848606 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9636. Min Act: -0.1700
Data Index: 2769407 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9794. Min Act: -0.1700
Data Index: 2443928 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1844. Min Range: -3.1844
Max Act: 2.9794. Min Act: -0.1700
Data Index: 8068380 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19