Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.6279. Min Act: -0.1700
Data Index: 7720807 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.5654. Min Act: -0.1700
Data Index: 5254278 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.5341. Min Act: -0.1700
Data Index: 1918414 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.5029. Min Act: -0.1700
Data Index: 6350640 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4716. Min Act: -0.1700
Data Index: 3905749 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4716. Min Act: -0.1700
Data Index: 7121763 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4716. Min Act: -0.1700
Data Index: 5113928 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4716. Min Act: -0.1700
Data Index: 3007140 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4716. Min Act: -0.1700
Data Index: 2827940 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4404. Min Act: -0.1700
Data Index: 8279257 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4091. Min Act: -0.1700
Data Index: 3907072 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4091. Min Act: -0.1700
Data Index: 6607719 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4091. Min Act: -0.1700
Data Index: 5015164 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4091. Min Act: -0.1700
Data Index: 5530060 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4091. Min Act: -0.1700
Data Index: 4423279 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.3779. Min Act: -0.1700
Data Index: 744872 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4091. Min Act: -0.1700
Data Index: 197015 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.3779. Min Act: -0.1700
Data Index: 1836621 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.3779. Min Act: -0.1700
Data Index: 7470682 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.3779. Min Act: -0.1700
Data Index: 7936757 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19