Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4643 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.2415. Min Act: -0.1700
Data Index: 1729633 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.2102. Min Act: -0.1700
Data Index: 3909481 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.2102. Min Act: -0.1700
Data Index: 2472643 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.1790. Min Act: -0.1700
Data Index: 6116812 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.1477. Min Act: -0.1700
Data Index: 4025208 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.0852. Min Act: -0.1700
Data Index: 7528334 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2415. Min Range: -5.2415
Max Act: 5.1165. Min Act: -0.1700
Data Index: 6306016 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9915. Min Act: -0.1700
Data Index: 5785250 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9915. Min Act: -0.1700
Data Index: 2356121 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9915. Min Act: -0.1700
Data Index: 5455180 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9602. Min Act: -0.1700
Data Index: 2847126 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9602. Min Act: -0.1700
Data Index: 5426164 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9290. Min Act: -0.1700
Data Index: 4046413 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9290. Min Act: -0.1700
Data Index: 6049802 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9290. Min Act: -0.1700
Data Index: 3695796 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9290. Min Act: -0.1700
Data Index: 1832715 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9290. Min Act: -0.1700
Data Index: 6626726 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9602. Min Act: -0.1700
Data Index: 6019968 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.9290. Min Act: -0.1700
Data Index: 367685 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2415. Min Range: -5.2415
Max Act: 4.8977. Min Act: -0.1700
Data Index: 295952 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19