Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2536 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.6102. Min Act: -0.1700
Data Index: 6848128 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.6415. Min Act: -0.1700
Data Index: 1088431 (Open Web Text)
Max Activating Token Index: 712
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: 7893999 (Open Web Text)
Max Activating Token Index: 206
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: 7063759 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.4852. Min Act: -0.1700
Data Index: 3407514 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3915. Min Act: -0.1700
Data Index: 8457020 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3915. Min Act: -0.1700
Data Index: 8092514 (Open Web Text)
Max Activating Token Index: 632
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: 2609798 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.3290. Min Act: -0.1700
Data Index: 981979 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2665. Min Act: -0.1700
Data Index: 2900556 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2040. Min Act: -0.1700
Data Index: 387654 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.1727. Min Act: -0.1700
Data Index: 7847669 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2040. Min Act: -0.1700
Data Index: 4056880 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2040. Min Act: -0.1700
Data Index: 6556408 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.2040. Min Act: -0.1700
Data Index: 4726317 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.1727. Min Act: -0.1700
Data Index: 8437202 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.1727. Min Act: -0.1700
Data Index: 7885970 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.1415. Min Act: -0.1700
Data Index: 8249382 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.1727. Min Act: -0.1700
Data Index: 4528593 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6415. Min Range: -6.6415
Max Act: 6.1102. Min Act: -0.1700
Data Index: 5888524 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19