Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.5710. Min Act: -0.1700
Data Index: 2084584 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.5710. Min Act: -0.1700
Data Index: 1804444 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.5397. Min Act: -0.1700
Data Index: 3750406 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.5085. Min Act: -0.1700
Data Index: 65589 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.4460. Min Act: -0.1700
Data Index: 1963144 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.4147. Min Act: -0.1700
Data Index: 2578602 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.4147. Min Act: -0.1700
Data Index: 3619597 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.4147. Min Act: -0.1700
Data Index: 7177715 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.3210. Min Act: -0.1700
Data Index: 4177481 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.3210. Min Act: -0.1700
Data Index: 1276683 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.3210. Min Act: -0.1700
Data Index: 7780940 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2897. Min Act: -0.1700
Data Index: 567182 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2897. Min Act: -0.1700
Data Index: 3781631 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2585. Min Act: -0.1700
Data Index: 5100520 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2585. Min Act: -0.1700
Data Index: 762318 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2585. Min Act: -0.1700
Data Index: 4847508 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2585. Min Act: -0.1700
Data Index: 214895 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2272. Min Act: -0.1700
Data Index: 2899965 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2272. Min Act: -0.1700
Data Index: 957266 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5710. Min Range: -6.5710
Max Act: 6.2272. Min Act: -0.1700
Data Index: 2107545 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19