Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.7231. Min Act: -0.1700
Data Index: 5574195 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.2544. Min Act: -0.1700
Data Index: 5526663 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.2544. Min Act: -0.1700
Data Index: 7744889 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.0981. Min Act: -0.1700
Data Index: 2110192 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.0981. Min Act: -0.1700
Data Index: 2250436 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.0356. Min Act: -0.1700
Data Index: 2078313 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.0356. Min Act: -0.1700
Data Index: 6351602 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7231. Min Range: -6.7231
Max Act: 6.0044. Min Act: -0.1700
Data Index: 67367 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9731. Min Act: -0.1700
Data Index: 2115096 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9731. Min Act: -0.1700
Data Index: 7017038 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9731. Min Act: -0.1700
Data Index: 499783 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9419. Min Act: -0.1700
Data Index: 3282045 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9419. Min Act: -0.1700
Data Index: 8808777 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9419. Min Act: -0.1700
Data Index: 7611228 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9106. Min Act: -0.1700
Data Index: 8239870 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9106. Min Act: -0.1700
Data Index: 1124158 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9419. Min Act: -0.1700
Data Index: 7136508 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9106. Min Act: -0.1700
Data Index: 6904721 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9419. Min Act: -0.1700
Data Index: 6342037 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7231. Min Range: -6.7231
Max Act: 5.9106. Min Act: -0.1700
Data Index: 6057564 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19