Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.7290. Min Act: -0.1700
Data Index: 5607614 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.5727. Min Act: -0.1700
Data Index: 3239487 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.3227. Min Act: -0.1700
Data Index: 7462090 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6410544 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.1665. Min Act: -0.1700
Data Index: 2519663 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6046695 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.0102. Min Act: -0.1700
Data Index: 7095459 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7290. Min Range: -7.7290
Max Act: 7.0102. Min Act: -0.1700
Data Index: 1979220 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.9477. Min Act: -0.1700
Data Index: 3766191 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.9477. Min Act: -0.1700
Data Index: 3953673 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.8227. Min Act: -0.1700
Data Index: 8648672 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.8227. Min Act: -0.1700
Data Index: 3781757 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7915. Min Act: -0.1700
Data Index: 8064994 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7602. Min Act: -0.1700
Data Index: 8285873 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 3798994 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 8571570 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 7106123 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 7730420 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.6977. Min Act: -0.1700
Data Index: 3205755 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7290. Min Range: -7.7290
Max Act: 6.7290. Min Act: -0.1700
Data Index: 582594 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19