Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5589 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2452. Min Range: -11.2452
Max Act: 11.2452. Min Act: -0.1700
Data Index: 6595084 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.8077. Min Act: -0.1700
Data Index: 6717232 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.6827. Min Act: -0.1700
Data Index: 4213853 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.6202. Min Act: -0.1700
Data Index: 4901312 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.5577. Min Act: -0.1700
Data Index: 2489481 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.4952. Min Act: -0.1700
Data Index: 3239418 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.4327. Min Act: -0.1700
Data Index: 2487023 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.4952. Min Act: -0.1700
Data Index: 987935 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.4952. Min Act: -0.1700
Data Index: 4470465 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.3702. Min Act: -0.1700
Data Index: 5603659 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.3702. Min Act: -0.1700
Data Index: 2085656 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.3702. Min Act: -0.1700
Data Index: 810602 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.3077. Min Act: -0.1700
Data Index: 7828217 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.3077. Min Act: -0.1700
Data Index: 4748349 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.2452. Min Act: -0.1700
Data Index: 130123 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.1827. Min Act: -0.1700
Data Index: 251101 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.1827. Min Act: -0.1700
Data Index: 1196603 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.1827. Min Act: -0.1700
Data Index: 1013044 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.1202. Min Act: -0.1700
Data Index: 6470116 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2452. Min Range: -11.2452
Max Act: 10.1202. Min Act: -0.1700
Data Index: 4032784 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19