Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5955. Min Range: -10.5955
Max Act: 10.5955. Min Act: -0.1700
Data Index: 287590 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5955. Min Range: -10.5955
Max Act: 10.3455. Min Act: -0.1700
Data Index: 1412494 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5955. Min Range: -10.5955
Max Act: 10.3455. Min Act: -0.1700
Data Index: 8554238 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.9705. Min Act: -0.1700
Data Index: 1898836 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.9705. Min Act: -0.1700
Data Index: 5743181 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.9080. Min Act: -0.1700
Data Index: 4369475 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.9080. Min Act: -0.1700
Data Index: 8134658 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.8455. Min Act: -0.1700
Data Index: 5427160 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.9080. Min Act: -0.1700
Data Index: 925031 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.7830. Min Act: -0.1700
Data Index: 6947050 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.7830. Min Act: -0.1700
Data Index: 915913 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.7205. Min Act: -0.1700
Data Index: 292941 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.6580. Min Act: -0.1700
Data Index: 3153069 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.6580. Min Act: -0.1700
Data Index: 5408939 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.5955. Min Act: -0.1700
Data Index: 1741992 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.6580. Min Act: -0.1700
Data Index: 6900600 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.5955. Min Act: -0.1700
Data Index: 8540323 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.5955. Min Act: -0.1700
Data Index: 142262 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.5330. Min Act: -0.1700
Data Index: 2515884 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5955. Min Range: -10.5955
Max Act: 9.5330. Min Act: -0.1700
Data Index: 6941211 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19