Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6326 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.8638. Min Act: -0.1700
Data Index: 7104428 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.7076. Min Act: -0.1700
Data Index: 6488036 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.7076. Min Act: -0.1700
Data Index: 8208324 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.5201. Min Act: -0.1700
Data Index: 412267 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.5201. Min Act: -0.1700
Data Index: 4429278 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.5513. Min Act: -0.1700
Data Index: 6892209 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.4263. Min Act: -0.1700
Data Index: 8522424 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.4576. Min Act: -0.1700
Data Index: 2475344 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.4576. Min Act: -0.1700
Data Index: 6356863 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.4263. Min Act: -0.1700
Data Index: 7538417 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3638. Min Act: -0.1700
Data Index: 1726445 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3013. Min Act: -0.1700
Data Index: 3821480 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3013. Min Act: -0.1700
Data Index: 1766894 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3013. Min Act: -0.1700
Data Index: 582315 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.2388. Min Act: -0.1700
Data Index: 4051511 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3013. Min Act: -0.1700
Data Index: 2749964 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3013. Min Act: -0.1700
Data Index: 327651 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.3013. Min Act: -0.1700
Data Index: 7308123 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.2388. Min Act: -0.1700
Data Index: 3500063 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8638. Min Range: -7.8638
Max Act: 7.2388. Min Act: -0.1700
Data Index: 20448 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19