Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5898 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.7036. Min Act: -0.1700
Data Index: 2076974 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.0161. Min Act: -0.1700
Data Index: 6249027 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9223. Min Act: -0.1700
Data Index: 869066 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.8911. Min Act: -0.1700
Data Index: 2056921 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.8911. Min Act: -0.1700
Data Index: 2123454 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.7973. Min Act: -0.1700
Data Index: 7128043 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.7036. Min Act: -0.1700
Data Index: 5829704 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.7036. Min Act: -0.1700
Data Index: 5779462 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.7036. Min Act: -0.1700
Data Index: 2482102 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.6411. Min Act: -0.1700
Data Index: 5698979 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.6411. Min Act: -0.1700
Data Index: 2579979 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5786. Min Act: -0.1700
Data Index: 5919944 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5786. Min Act: -0.1700
Data Index: 6389591 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5473. Min Act: -0.1700
Data Index: 2327873 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5473. Min Act: -0.1700
Data Index: 5142249 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5161. Min Act: -0.1700
Data Index: 4829341 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5161. Min Act: -0.1700
Data Index: 8228811 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5473. Min Act: -0.1700
Data Index: 4789428 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.5161. Min Act: -0.1700
Data Index: 6660482 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.4848. Min Act: -0.1700
Data Index: 1750316 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19