Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4922 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.7211. Min Act: -0.1700
Data Index: 3946712 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.3773. Min Act: -0.1700
Data Index: 2528837 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.4086. Min Act: -0.1700
Data Index: 713059 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.4086. Min Act: -0.1700
Data Index: 5857149 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.3773. Min Act: -0.1700
Data Index: 553648 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.3148. Min Act: -0.1700
Data Index: 1466328 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.3461. Min Act: -0.1700
Data Index: 3815135 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.3148. Min Act: -0.1700
Data Index: 8313499 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2836. Min Act: -0.1700
Data Index: 7666812 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2836. Min Act: -0.1700
Data Index: 468654 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2836. Min Act: -0.1700
Data Index: 2248593 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2523. Min Act: -0.1700
Data Index: 302792 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2211. Min Act: -0.1700
Data Index: 7026288 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2523. Min Act: -0.1700
Data Index: 8071525 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2211. Min Act: -0.1700
Data Index: 3351994 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2211. Min Act: -0.1700
Data Index: 2711146 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.2211. Min Act: -0.1700
Data Index: 2222570 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.1898. Min Act: -0.1700
Data Index: 3440390 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.1898. Min Act: -0.1700
Data Index: 3625949 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7211. Min Range: -5.7211
Max Act: 5.1586. Min Act: -0.1700
Data Index: 3488836 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19