Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5324 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5985. Min Range: -8.5985
Max Act: 8.5985. Min Act: -0.1700
Data Index: 6157334 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.9110. Min Act: -0.1700
Data Index: 269333 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.8797. Min Act: -0.1700
Data Index: 6205687 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.8485. Min Act: -0.1700
Data Index: 7332437 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.8485. Min Act: -0.1700
Data Index: 6163649 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.7860. Min Act: -0.1700
Data Index: 7338453 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.7547. Min Act: -0.1700
Data Index: 8768383 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.7547. Min Act: -0.1700
Data Index: 3415776 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.6610. Min Act: -0.1700
Data Index: 6572866 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.6610. Min Act: -0.1700
Data Index: 6924956 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5985. Min Act: -0.1700
Data Index: 7073086 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5672. Min Act: -0.1700
Data Index: 1625180 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5360. Min Act: -0.1700
Data Index: 1240441 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5360. Min Act: -0.1700
Data Index: 4782101 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5360. Min Act: -0.1700
Data Index: 2069917 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5047. Min Act: -0.1700
Data Index: 951235 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5360. Min Act: -0.1700
Data Index: 8491443 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.5360. Min Act: -0.1700
Data Index: 1283643 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.4422. Min Act: -0.1700
Data Index: 398780 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5985. Min Range: -8.5985
Max Act: 7.4110. Min Act: -0.1700
Data Index: 1627732 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19