Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1786. Min Range: -7.1786
Max Act: 7.1786. Min Act: -0.1700
Data Index: 811921 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1786. Min Range: -7.1786
Max Act: 7.1786. Min Act: -0.1700
Data Index: 702786 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1786. Min Range: -7.1786
Max Act: 7.0849. Min Act: -0.1700
Data Index: 8571604 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1786. Min Range: -7.1786
Max Act: 7.1161. Min Act: -0.1700
Data Index: 966743 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.9911. Min Act: -0.1700
Data Index: 4090346 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.8661. Min Act: -0.1700
Data Index: 42257 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.8974. Min Act: -0.1700
Data Index: 1004142 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.8661. Min Act: -0.1700
Data Index: 3138909 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.8349. Min Act: -0.1700
Data Index: 2222776 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.8349. Min Act: -0.1700
Data Index: 5378441 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.8349. Min Act: -0.1700
Data Index: 6919583 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.7099. Min Act: -0.1700
Data Index: 754568 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6786. Min Act: -0.1700
Data Index: 7160056 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.7099. Min Act: -0.1700
Data Index: 828876 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6474. Min Act: -0.1700
Data Index: 4114755 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6786. Min Act: -0.1700
Data Index: 6638944 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6786. Min Act: -0.1700
Data Index: 7944641 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6474. Min Act: -0.1700
Data Index: 4654801 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6161. Min Act: -0.1700
Data Index: 4654802 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1786. Min Range: -7.1786
Max Act: 6.6474. Min Act: -0.1700
Data Index: 7331923 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19