Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.8108. Min Act: -0.1700
Data Index: 185782 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.4983. Min Act: -0.1700
Data Index: 6775803 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.5608. Min Act: -0.1700
Data Index: 6110195 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.2483. Min Act: -0.1700
Data Index: 5859150 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.2170. Min Act: -0.1700
Data Index: 5292236 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.1233. Min Act: -0.1700
Data Index: 3818035 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8108. Min Range: -8.8108
Max Act: 8.1233. Min Act: -0.1700
Data Index: 2059828 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 7407008 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 5892252 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.9358. Min Act: -0.1700
Data Index: 355246 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.9045. Min Act: -0.1700
Data Index: 5604935 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.9045. Min Act: -0.1700
Data Index: 366329 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8733. Min Act: -0.1700
Data Index: 7267403 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8420. Min Act: -0.1700
Data Index: 3561328 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.9045. Min Act: -0.1700
Data Index: 5859148 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8420. Min Act: -0.1700
Data Index: 3818039 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8108. Min Act: -0.1700
Data Index: 4449579 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8733. Min Act: -0.1700
Data Index: 1284517 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8108. Min Act: -0.1700
Data Index: 5664174 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8108. Min Range: -8.8108
Max Act: 7.8420. Min Act: -0.1700
Data Index: 1906302 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19