Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.8354. Min Act: -0.1700
Data Index: 8262694 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.6792. Min Act: -0.1700
Data Index: 4977413 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6275824 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.5854. Min Act: -0.1700
Data Index: 3360935 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.5229. Min Act: -0.1700
Data Index: 6404436 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.4917. Min Act: -0.1700
Data Index: 2550315 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.4604. Min Act: -0.1700
Data Index: 2498697 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.4604. Min Act: -0.1700
Data Index: 4426451 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.4292. Min Act: -0.1700
Data Index: 7338544 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.3979. Min Act: -0.1700
Data Index: 2749117 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.3354. Min Act: -0.1700
Data Index: 5376169 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.3667. Min Act: -0.1700
Data Index: 7840415 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.3354. Min Act: -0.1700
Data Index: 89546 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.3042. Min Act: -0.1700
Data Index: 4784771 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.3042. Min Act: -0.1700
Data Index: 2006041 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.2417. Min Act: -0.1700
Data Index: 2383807 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.2104. Min Act: -0.1700
Data Index: 2049239 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.1792. Min Act: -0.1700
Data Index: 4255145 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.1792. Min Act: -0.1700
Data Index: 3437451 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8354. Min Range: -6.8354
Max Act: 6.1792. Min Act: -0.1700
Data Index: 3393021 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19