Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5038 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.7280. Min Act: -0.1700
Data Index: 5973870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.5190. Min Act: -0.1700
Data Index: 4958051 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.4704. Min Act: -0.1700
Data Index: 7651304 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.4542. Min Act: -0.1697
Data Index: 8787905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.4379. Min Act: -0.1700
Data Index: 2601695 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.4379. Min Act: -0.1699
Data Index: 3409719 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3890. Min Act: -0.1700
Data Index: 7693370 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3726. Min Act: -0.1700
Data Index: 8092520 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3563. Min Act: -0.1700
Data Index: 740862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3563. Min Act: -0.1700
Data Index: 4569579 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3399. Min Act: -0.1694
Data Index: 1191372 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3235. Min Act: -0.1700
Data Index: 703201 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3399. Min Act: -0.1700
Data Index: 8715019 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3399. Min Act: -0.1700
Data Index: 2611435 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3235. Min Act: -0.1700
Data Index: 4027584 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3235. Min Act: -0.1700
Data Index: 5973869 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.2906. Min Act: -0.1700
Data Index: 4634293 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3070. Min Act: -0.1674
Data Index: 6311678 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3070. Min Act: -0.1700
Data Index: 8624547 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7280. Min Range: -2.7280
Max Act: 2.3070. Min Act: -0.1700
Data Index: 5384235 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19