Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1034 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.8552. Min Act: -0.1700
Data Index: 6986864 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.8552. Min Act: -0.1700
Data Index: 8212545 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.7926. Min Act: -0.1700
Data Index: 2798308 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.7926. Min Act: -0.1700
Data Index: 6986863 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.7301. Min Act: -0.1700
Data Index: 2106286 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.7301. Min Act: -0.1700
Data Index: 6986862 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6988. Min Act: -0.1700
Data Index: 3726883 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6675. Min Act: -0.1700
Data Index: 2519253 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6675. Min Act: -0.1700
Data Index: 6359379 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6675. Min Act: -0.1700
Data Index: 6359373 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6675. Min Act: -0.1700
Data Index: 6988770 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6362. Min Act: -0.1700
Data Index: 2372832 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6362. Min Act: -0.1700
Data Index: 6359372 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6362. Min Act: -0.1700
Data Index: 6986865 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6049. Min Act: -0.1700
Data Index: 454653 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6362. Min Act: -0.1700
Data Index: 6470919 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6362. Min Act: -0.1700
Data Index: 8586863 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.6049. Min Act: -0.1700
Data Index: 341051 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.5736. Min Act: -0.1700
Data Index: 1921146 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8552. Min Range: -3.8552
Max Act: 3.5736. Min Act: -0.1700
Data Index: 1327986 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19