Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 374 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 7993649 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.5790. Min Act: -0.1700
Data Index: 5183423 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.5790. Min Act: -0.1700
Data Index: 5183424 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.5165. Min Act: -0.1700
Data Index: 1256571 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.5165. Min Act: -0.1700
Data Index: 5183425 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.4540. Min Act: -0.1700
Data Index: 1799200 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.4540. Min Act: -0.1700
Data Index: 8451844 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3915. Min Act: -0.1700
Data Index: 2489624 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3602. Min Act: -0.1700
Data Index: 1256567 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3602. Min Act: -0.1700
Data Index: 1799199 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3290. Min Act: -0.1700
Data Index: 2946048 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3290. Min Act: -0.1700
Data Index: 7766187 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3290. Min Act: -0.1700
Data Index: 5183426 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3290. Min Act: -0.1700
Data Index: 5756541 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3290. Min Act: -0.1700
Data Index: 5183427 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2977. Min Act: -0.1700
Data Index: 807001 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2977. Min Act: -0.1700
Data Index: 47427 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2665. Min Act: -0.1700
Data Index: 5756548 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2665. Min Act: -0.1700
Data Index: 1298883 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2977. Min Act: -0.1700
Data Index: 5183429 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19