Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3049. Min Range: -5.3049
Max Act: 5.3049. Min Act: -0.1700
Data Index: 6772667 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3049. Min Range: -5.3049
Max Act: 5.1486. Min Act: -0.1700
Data Index: 8071459 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3049. Min Range: -5.3049
Max Act: 5.1174. Min Act: -0.1700
Data Index: 3431780 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3049. Min Range: -5.3049
Max Act: 5.1174. Min Act: -0.1700
Data Index: 6853094 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3049. Min Range: -5.3049
Max Act: 5.0861. Min Act: -0.1700
Data Index: 5630749 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3049. Min Range: -5.3049
Max Act: 5.0236. Min Act: -0.1700
Data Index: 4335387 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.9611. Min Act: -0.1700
Data Index: 6066111 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.9611. Min Act: -0.1700
Data Index: 977318 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.9299. Min Act: -0.1700
Data Index: 3407782 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8986. Min Act: -0.1700
Data Index: 5415083 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8674. Min Act: -0.1700
Data Index: 4874205 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8674. Min Act: -0.1700
Data Index: 8247620 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8361. Min Act: -0.1700
Data Index: 6314391 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8049. Min Act: -0.1700
Data Index: 6159627 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8674. Min Act: -0.1700
Data Index: 2524019 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8049. Min Act: -0.1700
Data Index: 5839653 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8049. Min Act: -0.1700
Data Index: 3798008 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.7736. Min Act: -0.1700
Data Index: 1519595 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.8049. Min Act: -0.1700
Data Index: 822684 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3049. Min Range: -5.3049
Max Act: 4.7736. Min Act: -0.1700
Data Index: 5573477 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19