Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.7711. Min Act: -0.1700
Data Index: 1609566 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.7242. Min Act: -0.1700
Data Index: 7306874 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.7085. Min Act: -0.1700
Data Index: 4523000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.6616. Min Act: -0.1700
Data Index: 593724 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.6459. Min Act: -0.1700
Data Index: 5942821 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.6459. Min Act: -0.1700
Data Index: 6378305 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.6459. Min Act: -0.1700
Data Index: 4665153 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5990. Min Act: -0.1700
Data Index: 3228477 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5677. Min Act: -0.1700
Data Index: 7213564 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5520. Min Act: -0.1700
Data Index: 1843839 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5520. Min Act: -0.1700
Data Index: 1977111 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5364. Min Act: -0.1700
Data Index: 24581 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5207. Min Act: -0.1700
Data Index: 7510709 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5364. Min Act: -0.1700
Data Index: 5747089 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5051. Min Act: -0.1700
Data Index: 7156400 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5051. Min Act: -0.1700
Data Index: 178510 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5207. Min Act: -0.1700
Data Index: 8077277 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.5051. Min Act: -0.1700
Data Index: 6410842 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.4894. Min Act: -0.1700
Data Index: 4575156 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7711. Min Range: -3.7711
Max Act: 3.4894. Min Act: -0.1700
Data Index: 4243569 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19