Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.4877. Min Act: -0.1700
Data Index: 6221045 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.3627. Min Act: -0.1700
Data Index: 277462 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.3627. Min Act: -0.1700
Data Index: 3450795 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.2377. Min Act: -0.1700
Data Index: 748026 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.2377. Min Act: -0.1700
Data Index: 4943563 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.1752. Min Act: -0.1700
Data Index: 6208224 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9877. Min Act: -0.1700
Data Index: 8319007 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9877. Min Act: -0.1700
Data Index: 6133883 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4877. Min Range: -7.4877
Max Act: 7.0189. Min Act: -0.1700
Data Index: 4117495 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9564. Min Act: -0.1700
Data Index: 2921054 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9564. Min Act: -0.1700
Data Index: 7999788 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9564. Min Act: -0.1700
Data Index: 7629982 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9252. Min Act: -0.1700
Data Index: 8482980 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9252. Min Act: -0.1700
Data Index: 3037805 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.9252. Min Act: -0.1700
Data Index: 3913205 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.8939. Min Act: -0.1700
Data Index: 5778353 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.8939. Min Act: -0.1700
Data Index: 871305 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7731516 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.8939. Min Act: -0.1700
Data Index: 5279353 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4877. Min Range: -7.4877
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7726272 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19