Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.5348. Min Act: -0.1700
Data Index: 5007744 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.5036. Min Act: -0.1700
Data Index: 8475841 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.1598. Min Act: -0.1700
Data Index: 2293634 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.1286. Min Act: -0.1700
Data Index: 5040436 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0973. Min Act: -0.1700
Data Index: 1049458 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0661. Min Act: -0.1700
Data Index: 3824442 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0661. Min Act: -0.1700
Data Index: 2314476 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0348. Min Act: -0.1700
Data Index: 2444362 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0036. Min Act: -0.1700
Data Index: 2638264 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0036. Min Act: -0.1700
Data Index: 5638712 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5348. Min Range: -7.5348
Max Act: 7.0036. Min Act: -0.1700
Data Index: 4235265 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.9723. Min Act: -0.1700
Data Index: 187312 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.9723. Min Act: -0.1700
Data Index: 7820631 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6145012 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.9411. Min Act: -0.1700
Data Index: 5802980 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.8786. Min Act: -0.1700
Data Index: 6980637 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.8786. Min Act: -0.1700
Data Index: 7097882 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.8786. Min Act: -0.1700
Data Index: 3824311 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.8786. Min Act: -0.1700
Data Index: 4766494 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5348. Min Range: -7.5348
Max Act: 6.8786. Min Act: -0.1700
Data Index: 2440836 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19