Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0620. Min Range: -6.0620
Max Act: 6.0620. Min Act: -0.1700
Data Index: 1279710 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.6557. Min Act: -0.1700
Data Index: 3930566 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.5932. Min Act: -0.1700
Data Index: 2621649 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.6245. Min Act: -0.1700
Data Index: 8080386 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.5932. Min Act: -0.1700
Data Index: 184952 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.5620. Min Act: -0.1700
Data Index: 8522889 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.5620. Min Act: -0.1700
Data Index: 1931763 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.4370. Min Act: -0.1700
Data Index: 784865 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.4057. Min Act: -0.1700
Data Index: 114533 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.4057. Min Act: -0.1700
Data Index: 3581729 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.3745. Min Act: -0.1700
Data Index: 7277445 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.3432. Min Act: -0.1700
Data Index: 2411774 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.3120. Min Act: -0.1700
Data Index: 8003965 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.3120. Min Act: -0.1700
Data Index: 3347317 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.2182. Min Act: -0.1700
Data Index: 5371457 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.2495. Min Act: -0.1700
Data Index: 3416970 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.2182. Min Act: -0.1700
Data Index: 2901473 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.2182. Min Act: -0.1700
Data Index: 2655246 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.1557. Min Act: -0.1700
Data Index: 6154433 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0620. Min Range: -6.0620
Max Act: 5.1557. Min Act: -0.1700
Data Index: 2022658 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19