Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.1897. Min Act: -0.1700
Data Index: 513100 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.1897. Min Act: -0.1700
Data Index: 1232997 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0959. Min Act: -0.1700
Data Index: 2091084 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0959. Min Act: -0.1700
Data Index: 7033178 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0647. Min Act: -0.1700
Data Index: 7819979 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0334. Min Act: -0.1700
Data Index: 3081490 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0022. Min Act: -0.1700
Data Index: 7179687 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0022. Min Act: -0.1700
Data Index: 6576407 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1897. Min Range: -7.1897
Max Act: 7.0022. Min Act: -0.1700
Data Index: 7622587 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.9709. Min Act: -0.1700
Data Index: 1638234 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.9709. Min Act: -0.1700
Data Index: 6352779 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.9084. Min Act: -0.1700
Data Index: 4120051 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.9084. Min Act: -0.1700
Data Index: 225346 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.8459. Min Act: -0.1700
Data Index: 6567737 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.8147. Min Act: -0.1700
Data Index: 3081489 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.7834. Min Act: -0.1700
Data Index: 8101278 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.8147. Min Act: -0.1700
Data Index: 3676218 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.7522. Min Act: -0.1700
Data Index: 6016177 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.8147. Min Act: -0.1700
Data Index: 7480188 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1897. Min Range: -7.1897
Max Act: 6.7834. Min Act: -0.1700
Data Index: 2402972 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19