Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.7556. Min Act: -0.1700
Data Index: 6306528 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.7556. Min Act: -0.1700
Data Index: 1646415 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5681. Min Act: -0.1700
Data Index: 8268692 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5681. Min Act: -0.1700
Data Index: 3975413 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5681. Min Act: -0.1700
Data Index: 54549 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5681. Min Act: -0.1700
Data Index: 299401 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5681. Min Act: -0.1700
Data Index: 1073330 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5056. Min Act: -0.1700
Data Index: 7686184 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.4431. Min Act: -0.1700
Data Index: 4968326 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.5056. Min Act: -0.1700
Data Index: 54550 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.4431. Min Act: -0.1700
Data Index: 7688476 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.4431. Min Act: -0.1700
Data Index: 8120145 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.3806. Min Act: -0.1700
Data Index: 4834252 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.3806. Min Act: -0.1700
Data Index: 1240223 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.3806. Min Act: -0.1700
Data Index: 6175458 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.2556. Min Act: -0.1700
Data Index: 8708173 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.2243. Min Act: -0.1700
Data Index: 4748704 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.2556. Min Act: -0.1700
Data Index: 1604422 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.2243. Min Act: -0.1700
Data Index: 3697494 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7556. Min Range: -7.7556
Max Act: 7.2243. Min Act: -0.1700
Data Index: 2018524 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19