Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1273. Min Range: -5.1273
Max Act: 5.1273. Min Act: -0.1700
Data Index: 1002968 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1273. Min Range: -5.1273
Max Act: 5.0960. Min Act: -0.1700
Data Index: 1295051 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.7835. Min Act: -0.1700
Data Index: 1366290 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.7523. Min Act: -0.1700
Data Index: 914512 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.7210. Min Act: -0.1700
Data Index: 1481535 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.7210. Min Act: -0.1700
Data Index: 7878451 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6898. Min Act: -0.1700
Data Index: 7922962 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6898. Min Act: -0.1700
Data Index: 5788507 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6898. Min Act: -0.1700
Data Index: 3632941 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6585. Min Act: -0.1700
Data Index: 5530374 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6273. Min Act: -0.1700
Data Index: 4747052 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6273. Min Act: -0.1700
Data Index: 4407762 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6273. Min Act: -0.1700
Data Index: 5470695 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.5960. Min Act: -0.1700
Data Index: 8047319 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.6273. Min Act: -0.1700
Data Index: 5484951 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.5960. Min Act: -0.1700
Data Index: 543601 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.5960. Min Act: -0.1700
Data Index: 2928231 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.5960. Min Act: -0.1700
Data Index: 5326924 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.5648. Min Act: -0.1700
Data Index: 4120382 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1273. Min Range: -5.1273
Max Act: 4.5648. Min Act: -0.1700
Data Index: 2952007 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19