Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.4347. Min Act: -0.1700
Data Index: 2459264 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.4034. Min Act: -0.1700
Data Index: 1518099 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.2784. Min Act: -0.1700
Data Index: 5116330 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.2784. Min Act: -0.1700
Data Index: 6803816 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.0909. Min Act: -0.1700
Data Index: 3917992 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.0909. Min Act: -0.1700
Data Index: 737570 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.0284. Min Act: -0.1700
Data Index: 7386975 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.0284. Min Act: -0.1700
Data Index: 4369834 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4347. Min Range: -7.4347
Max Act: 7.0284. Min Act: -0.1700
Data Index: 425111 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9347. Min Act: -0.1700
Data Index: 504427 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9972. Min Act: -0.1700
Data Index: 5825484 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9347. Min Act: -0.1700
Data Index: 1084683 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9347. Min Act: -0.1700
Data Index: 3882521 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9034. Min Act: -0.1700
Data Index: 1546173 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9034. Min Act: -0.1700
Data Index: 5538019 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.8722. Min Act: -0.1700
Data Index: 2310090 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.9034. Min Act: -0.1700
Data Index: 4098969 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.8722. Min Act: -0.1700
Data Index: 7887626 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.8722. Min Act: -0.1700
Data Index: 8625891 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4347. Min Range: -7.4347
Max Act: 6.8722. Min Act: -0.1700
Data Index: 3368723 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19