Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2940. Min Range: -5.2940
Max Act: 5.2940. Min Act: -0.1700
Data Index: 5824534 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.9190. Min Act: -0.1700
Data Index: 6624633 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.9190. Min Act: -0.1700
Data Index: 8683463 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.8565. Min Act: -0.1700
Data Index: 6431071 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.8565. Min Act: -0.1700
Data Index: 3236002 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.8565. Min Act: -0.1700
Data Index: 2131963 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.8252. Min Act: -0.1700
Data Index: 6558363 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7627. Min Act: -0.1700
Data Index: 7738477 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7940. Min Act: -0.1700
Data Index: 5097979 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7627. Min Act: -0.1700
Data Index: 1152016 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7940. Min Act: -0.1700
Data Index: 2332977 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.8252. Min Act: -0.1700
Data Index: 1507855 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7315. Min Act: -0.1700
Data Index: 8167698 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7315. Min Act: -0.1700
Data Index: 5795233 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7315. Min Act: -0.1700
Data Index: 8611643 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7315. Min Act: -0.1700
Data Index: 8328223 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.6690. Min Act: -0.1700
Data Index: 860687 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7002. Min Act: -0.1700
Data Index: 5850315 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.7002. Min Act: -0.1700
Data Index: 1560976 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2940. Min Range: -5.2940
Max Act: 4.6690. Min Act: -0.1700
Data Index: 5452729 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19