Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.8817. Min Act: -0.1700
Data Index: 3482196 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.8504. Min Act: -0.1700
Data Index: 7301775 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.6317. Min Act: -0.1700
Data Index: 347232 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.5379. Min Act: -0.1700
Data Index: 5381188 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.5067. Min Act: -0.1700
Data Index: 7513713 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.4442. Min Act: -0.1700
Data Index: 1668123 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.4129. Min Act: -0.1700
Data Index: 4413768 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.4129. Min Act: -0.1700
Data Index: 3437478 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3817. Min Act: -0.1700
Data Index: 3124428 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3817. Min Act: -0.1700
Data Index: 92376 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3504. Min Act: -0.1700
Data Index: 7906620 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3504. Min Act: -0.1700
Data Index: 4051795 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3504. Min Act: -0.1700
Data Index: 2385420 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3504. Min Act: -0.1700
Data Index: 8534981 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3504. Min Act: -0.1700
Data Index: 2119171 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3192. Min Act: -0.1700
Data Index: 1522805 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3192. Min Act: -0.1700
Data Index: 592255 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3192. Min Act: -0.1700
Data Index: 5844282 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3192. Min Act: -0.1700
Data Index: 7323868 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8817. Min Range: -6.8817
Max Act: 6.3192. Min Act: -0.1700
Data Index: 1637226 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19