Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.4883. Min Act: -0.1700
Data Index: 6783986 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.3633. Min Act: -0.1700
Data Index: 2475240 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.3008. Min Act: -0.1700
Data Index: 2560474 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.2071. Min Act: -0.1700
Data Index: 4607081 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.2071. Min Act: -0.1700
Data Index: 5985562 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.1758. Min Act: -0.1700
Data Index: 102420 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.0508. Min Act: -0.1700
Data Index: 636796 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.0508. Min Act: -0.1700
Data Index: 3868239 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4883. Min Range: -6.4883
Max Act: 6.0196. Min Act: -0.1700
Data Index: 1422582 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.9883. Min Act: -0.1700
Data Index: 6875237 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.9571. Min Act: -0.1700
Data Index: 2998311 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.9258. Min Act: -0.1700
Data Index: 2867606 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.9258. Min Act: -0.1700
Data Index: 5139426 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8946. Min Act: -0.1700
Data Index: 8612513 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8946. Min Act: -0.1700
Data Index: 777231 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8946. Min Act: -0.1700
Data Index: 8292301 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8633. Min Act: -0.1700
Data Index: 5199881 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8321. Min Act: -0.1700
Data Index: 4865830 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8321. Min Act: -0.1700
Data Index: 3235606 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4883. Min Range: -6.4883
Max Act: 5.8321. Min Act: -0.1700
Data Index: 1422487 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19