Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4181. Min Range: -11.4181
Max Act: 11.4181. Min Act: -0.1700
Data Index: 5013161 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4181. Min Range: -11.4181
Max Act: 11.3556. Min Act: -0.1700
Data Index: 4710623 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4181. Min Range: -11.4181
Max Act: 11.0431. Min Act: -0.1700
Data Index: 8724654 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4181. Min Range: -11.4181
Max Act: 11.0431. Min Act: -0.1700
Data Index: 356021 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4181. Min Range: -11.4181
Max Act: 11.0431. Min Act: -0.1700
Data Index: 7487456 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.9181. Min Act: -0.1700
Data Index: 3406276 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.9181. Min Act: -0.1700
Data Index: 5147888 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.9181. Min Act: -0.1700
Data Index: 5835380 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.8556. Min Act: -0.1700
Data Index: 5835381 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.7931. Min Act: -0.1700
Data Index: 5835379 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.7931. Min Act: -0.1700
Data Index: 6306463 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.7931. Min Act: -0.1700
Data Index: 2937295 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.7931. Min Act: -0.1700
Data Index: 920671 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.7931. Min Act: -0.1700
Data Index: 8724655 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.6681. Min Act: -0.1700
Data Index: 184698 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.7306. Min Act: -0.1700
Data Index: 7603473 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.6681. Min Act: -0.1700
Data Index: 4550004 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.6681. Min Act: -0.1700
Data Index: 74249 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.6681. Min Act: -0.1700
Data Index: 4045760 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4181. Min Range: -11.4181
Max Act: 10.6681. Min Act: -0.1700
Data Index: 2215084 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19