Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.2017. Min Act: -0.1700
Data Index: 3340822 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.2017. Min Act: -0.1700
Data Index: 8618158 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.2017. Min Act: -0.1700
Data Index: 3556033 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1851. Min Act: -0.1700
Data Index: 6823170 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1851. Min Act: -0.1700
Data Index: 3781769 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1685. Min Act: -0.1700
Data Index: 7109366 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1685. Min Act: -0.1700
Data Index: 1406923 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1685. Min Act: -0.1700
Data Index: 8803192 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1685. Min Act: -0.1700
Data Index: 7628349 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1685. Min Act: -0.1700
Data Index: 8040969 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1518. Min Act: -0.1700
Data Index: 3101459 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1518. Min Act: -0.1700
Data Index: 4776783 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1518. Min Act: -0.1700
Data Index: 7224173 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1351. Min Act: -0.1700
Data Index: 5105517 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1351. Min Act: -0.1700
Data Index: 6642584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1351. Min Act: -0.1700
Data Index: 6380494 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1351. Min Act: -0.1700
Data Index: 5631315 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1184. Min Act: -0.1700
Data Index: 378718 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1017. Min Act: -0.1700
Data Index: 6138455 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2017. Min Range: -2.2017
Max Act: 2.1351. Min Act: -0.1700
Data Index: 6487362 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19