Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.3293. Min Act: -0.1700
Data Index: 4381690 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.2668. Min Act: -0.1700
Data Index: 8471364 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.2043. Min Act: -0.1700
Data Index: 4487667 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.1418. Min Act: -0.1700
Data Index: 1478002 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.0793. Min Act: -0.1700
Data Index: 3859709 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.0793. Min Act: -0.1700
Data Index: 800513 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.0168. Min Act: -0.1700
Data Index: 2305864 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3293. Min Range: -8.3293
Max Act: 8.0168. Min Act: -0.1700
Data Index: 6707135 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 2533392 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 7494101 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 2793850 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 4444989 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 4823697 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 5971766 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 4106426 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.8918. Min Act: -0.1700
Data Index: 1762880 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.8918. Min Act: -0.1700
Data Index: 2964855 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.9543. Min Act: -0.1700
Data Index: 6479493 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.8918. Min Act: -0.1700
Data Index: 6130975 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3293. Min Range: -8.3293
Max Act: 7.8606. Min Act: -0.1700
Data Index: 4163009 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19