Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2565. Min Range: -8.2565
Max Act: 8.2565. Min Act: -0.1700
Data Index: 1887177 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2565. Min Range: -8.2565
Max Act: 8.1315. Min Act: -0.1700
Data Index: 6281292 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2565. Min Range: -8.2565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 8188274 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2565. Min Range: -8.2565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 3398206 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.9440. Min Act: -0.1700
Data Index: 3207992 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2565. Min Range: -8.2565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 5597999 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2565. Min Range: -8.2565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 7603307 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.9440. Min Act: -0.1700
Data Index: 1163277 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.9440. Min Act: -0.1700
Data Index: 4547310 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8815. Min Act: -0.1700
Data Index: 8168369 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8815. Min Act: -0.1700
Data Index: 8746255 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8815. Min Act: -0.1700
Data Index: 2410103 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8815. Min Act: -0.1700
Data Index: 4989415 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8815. Min Act: -0.1700
Data Index: 1842255 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8190. Min Act: -0.1700
Data Index: 4431219 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8190. Min Act: -0.1700
Data Index: 2972449 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8190. Min Act: -0.1700
Data Index: 6495336 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.8190. Min Act: -0.1700
Data Index: 5777549 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.7565. Min Act: -0.1699
Data Index: 3062140 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2565. Min Range: -8.2565
Max Act: 7.6940. Min Act: -0.1700
Data Index: 1722002 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19