Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 888 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.7284. Min Act: -0.1700
Data Index: 6803304 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6971. Min Act: -0.1700
Data Index: 2131073 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6971. Min Act: -0.1700
Data Index: 1001868 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6658. Min Act: -0.1700
Data Index: 1559351 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6345. Min Act: -0.1700
Data Index: 8718659 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6345. Min Act: -0.1700
Data Index: 3592476 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6189. Min Act: -0.1700
Data Index: 3135189 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.6189. Min Act: -0.1700
Data Index: 2190152 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5876. Min Act: -0.1700
Data Index: 2632008 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5719. Min Act: -0.1700
Data Index: 7874843 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5563. Min Act: -0.1700
Data Index: 3354075 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5563. Min Act: -0.1700
Data Index: 2628403 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5406. Min Act: -0.1700
Data Index: 3771318 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5406. Min Act: -0.1700
Data Index: 5448303 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.4936. Min Act: -0.1700
Data Index: 5845049 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5250. Min Act: -0.1700
Data Index: 4190521 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.5093. Min Act: -0.1700
Data Index: 1534926 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.4936. Min Act: -0.1700
Data Index: 8256048 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.4780. Min Act: -0.1700
Data Index: 4281613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7284. Min Range: -3.7284
Max Act: 3.4780. Min Act: -0.1700
Data Index: 4135597 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19