Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.5097. Min Act: -0.1700
Data Index: 2024883 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.5409. Min Act: -0.1700
Data Index: 5142043 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.5409. Min Act: -0.1700
Data Index: 5558119 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.4472. Min Act: -0.1700
Data Index: 2161689 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.4472. Min Act: -0.1700
Data Index: 628658 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.4472. Min Act: -0.1700
Data Index: 8578913 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.4472. Min Act: -0.1700
Data Index: 3155042 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.4159. Min Act: -0.1700
Data Index: 3070333 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.3847. Min Act: -0.1700
Data Index: 6868282 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.3222. Min Act: -0.1700
Data Index: 3766001 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.3847. Min Act: -0.1700
Data Index: 314334 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.3534. Min Act: -0.1700
Data Index: 7608285 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.3222. Min Act: -0.1700
Data Index: 6130765 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2909. Min Act: -0.1700
Data Index: 2184244 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2597. Min Act: -0.1700
Data Index: 2972235 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2597. Min Act: -0.1700
Data Index: 1226766 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2284. Min Act: -0.1700
Data Index: 1885291 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2284. Min Act: -0.1700
Data Index: 471903 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2284. Min Act: -0.1700
Data Index: 4618241 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5409. Min Range: -5.5409
Max Act: 5.2284. Min Act: -0.1700
Data Index: 217566 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19