Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.6368. Min Act: -0.1700
Data Index: 8182459 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.6368. Min Act: -0.1700
Data Index: 3022686 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.5430. Min Act: -0.1700
Data Index: 6805928 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.5118. Min Act: -0.1700
Data Index: 1182540 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4805. Min Act: -0.1700
Data Index: 8777042 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4805. Min Act: -0.1700
Data Index: 2594647 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4805. Min Act: -0.1700
Data Index: 8334940 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4493. Min Act: -0.1700
Data Index: 4747007 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4493. Min Act: -0.1700
Data Index: 8405222 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4493. Min Act: -0.1700
Data Index: 39352 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4180. Min Act: -0.1700
Data Index: 6246746 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4180. Min Act: -0.1700
Data Index: 5237586 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4493. Min Act: -0.1700
Data Index: 1132595 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.3868. Min Act: -0.1700
Data Index: 8317935 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.3868. Min Act: -0.1700
Data Index: 1466102 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.4180. Min Act: -0.1700
Data Index: 7080847 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.3868. Min Act: -0.1700
Data Index: 7400231 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.3868. Min Act: -0.1700
Data Index: 8405994 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.3868. Min Act: -0.1700
Data Index: 7990929 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6368. Min Range: -5.6368
Max Act: 5.3555. Min Act: -0.1700
Data Index: 5506763 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19