Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0612. Min Range: -8.0612
Max Act: 8.0612. Min Act: -0.1700
Data Index: 6494056 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0612. Min Range: -8.0612
Max Act: 8.0612. Min Act: -0.1700
Data Index: 7851360 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0612. Min Range: -8.0612
Max Act: 8.0612. Min Act: -0.1700
Data Index: 410726 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.9362. Min Act: -0.1700
Data Index: 3009393 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.8737. Min Act: -0.1700
Data Index: 243846 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.8737. Min Act: -0.1700
Data Index: 514719 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.8112. Min Act: -0.1700
Data Index: 5990930 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.8112. Min Act: -0.1700
Data Index: 4269714 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.7487. Min Act: -0.1700
Data Index: 8023937 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.7487. Min Act: -0.1700
Data Index: 6499134 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.7487. Min Act: -0.1700
Data Index: 3523675 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.6862. Min Act: -0.1700
Data Index: 393583 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.6862. Min Act: -0.1700
Data Index: 7172602 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.5612. Min Act: -0.1700
Data Index: 692508 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.6237. Min Act: -0.1700
Data Index: 7282245 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.5612. Min Act: -0.1700
Data Index: 2758057 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.5612. Min Act: -0.1700
Data Index: 6772562 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.5612. Min Act: -0.1700
Data Index: 50759 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.5612. Min Act: -0.1700
Data Index: 2435097 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0612. Min Range: -8.0612
Max Act: 7.5612. Min Act: -0.1700
Data Index: 5444424 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19