Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.3576. Min Act: -0.1700
Data Index: 3779903 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.2948. Min Act: -0.1700
Data Index: 6722796 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.2791. Min Act: -0.1700
Data Index: 4245253 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.2005. Min Act: -0.1700
Data Index: 5414710 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1848. Min Act: -0.1700
Data Index: 6048015 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1533. Min Act: -0.1700
Data Index: 6752198 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1691. Min Act: -0.1700
Data Index: 3084783 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1691. Min Act: -0.1700
Data Index: 3106145 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1691. Min Act: -0.1700
Data Index: 5727301 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1376. Min Act: -0.1700
Data Index: 3986129 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1376. Min Act: -0.1700
Data Index: 5482511 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1061. Min Act: -0.1700
Data Index: 26080 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1218. Min Act: -0.1700
Data Index: 7292926 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1218. Min Act: -0.1700
Data Index: 7602936 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1061. Min Act: -0.1700
Data Index: 5462582 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1218. Min Act: -0.1700
Data Index: 755435 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.1061. Min Act: -0.1700
Data Index: 8451323 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.0903. Min Act: -0.1700
Data Index: 1889215 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.0903. Min Act: -0.1700
Data Index: 1493960 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3576. Min Range: -3.3576
Max Act: 3.0903. Min Act: -0.1700
Data Index: 4775108 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19