Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.3619. Min Act: -0.1700
Data Index: 6898576 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.3619. Min Act: -0.1700
Data Index: 3580682 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.3306. Min Act: -0.1700
Data Index: 8337789 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.3306. Min Act: -0.1700
Data Index: 2820540 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2994. Min Act: -0.1700
Data Index: 6035455 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2994. Min Act: -0.1700
Data Index: 5809640 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2369. Min Act: -0.1700
Data Index: 1579625 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2369. Min Act: -0.1700
Data Index: 4566523 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2369. Min Act: -0.1700
Data Index: 4784801 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2056. Min Act: -0.1700
Data Index: 1778822 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1744. Min Act: -0.1700
Data Index: 1022200 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1431. Min Act: -0.1700
Data Index: 8465287 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1119. Min Act: -0.1700
Data Index: 3962648 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1119. Min Act: -0.1700
Data Index: 188261 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3011422 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 4009595 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3727391 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2443980 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 3251295 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 5202366 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19