Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5000 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.8876. Min Act: -0.1700
Data Index: 4024359 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.8251. Min Act: -0.1700
Data Index: 1360701 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.8251. Min Act: -0.1700
Data Index: 451792 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.7626. Min Act: -0.1700
Data Index: 5209129 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.5751. Min Act: -0.1700
Data Index: 4729478 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.5751. Min Act: -0.1700
Data Index: 269148 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.5751. Min Act: -0.1700
Data Index: 5725863 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.4501. Min Act: -0.1700
Data Index: 5970738 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.4501. Min Act: -0.1700
Data Index: 4460430 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3876. Min Act: -0.1700
Data Index: 5540203 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3876. Min Act: -0.1700
Data Index: 2908193 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3876. Min Act: -0.1700
Data Index: 3785989 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3876. Min Act: -0.1700
Data Index: 2451808 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3876. Min Act: -0.1700
Data Index: 5839364 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3876. Min Act: -0.1700
Data Index: 115777 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3251. Min Act: -0.1700
Data Index: 7285823 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3251. Min Act: -0.1700
Data Index: 3082924 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.3251. Min Act: -0.1700
Data Index: 3498308 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.2626. Min Act: -0.1700
Data Index: 805321 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8876. Min Range: -10.8876
Max Act: 10.2626. Min Act: -0.1700
Data Index: 5285379 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19