Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 810 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2573. Min Range: -5.2573
Max Act: 5.2573. Min Act: -0.1700
Data Index: 5925105 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2573. Min Range: -5.2573
Max Act: 5.1948. Min Act: -0.1700
Data Index: 6324329 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2573. Min Range: -5.2573
Max Act: 5.1323. Min Act: -0.1700
Data Index: 8455653 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2573. Min Range: -5.2573
Max Act: 5.0698. Min Act: -0.1700
Data Index: 4298853 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2573. Min Range: -5.2573
Max Act: 5.0385. Min Act: -0.1700
Data Index: 6773863 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2573. Min Range: -5.2573
Max Act: 5.0073. Min Act: -0.1700
Data Index: 4216039 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9760. Min Act: -0.1700
Data Index: 6113077 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9448. Min Act: -0.1700
Data Index: 3401661 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9448. Min Act: -0.1700
Data Index: 3206977 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9448. Min Act: -0.1700
Data Index: 7645078 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9448. Min Act: -0.1700
Data Index: 4298839 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9135. Min Act: -0.1700
Data Index: 6120347 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9135. Min Act: -0.1700
Data Index: 4298846 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9135. Min Act: -0.1700
Data Index: 4008566 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.9135. Min Act: -0.1700
Data Index: 7577630 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.8823. Min Act: -0.1700
Data Index: 2500075 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.8823. Min Act: -0.1700
Data Index: 6163790 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.8823. Min Act: -0.1700
Data Index: 720672 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.8823. Min Act: -0.1700
Data Index: 8602341 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2573. Min Range: -5.2573
Max Act: 4.8823. Min Act: -0.1700
Data Index: 855829 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19