Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 6123286 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 1926047 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.2290. Min Act: -0.1700
Data Index: 7625189 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.1978. Min Act: -0.1700
Data Index: 2067872 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.1040. Min Act: -0.1700
Data Index: 1390460 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0728. Min Act: -0.1700
Data Index: 4527205 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0728. Min Act: -0.1700
Data Index: 6667378 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0728. Min Act: -0.1700
Data Index: 8438306 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0728. Min Act: -0.1700
Data Index: 2461752 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0415. Min Act: -0.1700
Data Index: 71512 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0415. Min Act: -0.1700
Data Index: 7887171 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0103. Min Act: -0.1700
Data Index: 518306 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9790. Min Act: -0.1700
Data Index: 3222706 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9790. Min Act: -0.1700
Data Index: 1057539 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9790. Min Act: -0.1700
Data Index: 6904961 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9478. Min Act: -0.1700
Data Index: 2426118 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9478. Min Act: -0.1700
Data Index: 3252679 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9478. Min Act: -0.1700
Data Index: 4735282 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9165. Min Act: -0.1700
Data Index: 2487779 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9165. Min Act: -0.1700
Data Index: 4703802 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19