Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.6068. Min Act: -0.1700
Data Index: 2390256 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5912. Min Act: -0.1700
Data Index: 522806 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5912. Min Act: -0.1700
Data Index: 5675111 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5755. Min Act: -0.1700
Data Index: 537187 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5755. Min Act: -0.1700
Data Index: 4917743 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5599. Min Act: -0.1700
Data Index: 2188220 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5442. Min Act: -0.1700
Data Index: 8133272 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5286. Min Act: -0.1700
Data Index: 2795266 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5286. Min Act: -0.1700
Data Index: 5877221 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5129. Min Act: -0.1700
Data Index: 1883872 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.5286. Min Act: -0.1700
Data Index: 5685168 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4659. Min Act: -0.1700
Data Index: 8692984 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4816. Min Act: -0.1700
Data Index: 1116286 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4816. Min Act: -0.1700
Data Index: 2175798 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4659. Min Act: -0.1700
Data Index: 7893324 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4659. Min Act: -0.1700
Data Index: 9579 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4659. Min Act: -0.1700
Data Index: 215049 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4502. Min Act: -0.1700
Data Index: 1589218 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.4032. Min Act: -0.1700
Data Index: 5524369 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6068. Min Range: -3.6068
Max Act: 3.3719. Min Act: -0.1700
Data Index: 2119210 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19