Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5595 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.8584. Min Act: -0.1700
Data Index: 4445368 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.7646. Min Act: -0.1700
Data Index: 3766136 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.7334. Min Act: -0.1700
Data Index: 2512670 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.6709. Min Act: -0.1700
Data Index: 2084074 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.6084. Min Act: -0.1700
Data Index: 4291457 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.6084. Min Act: -0.1700
Data Index: 7081554 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.5771. Min Act: -0.1700
Data Index: 2447902 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.5459. Min Act: -0.1700
Data Index: 4426923 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.5146. Min Act: -0.1700
Data Index: 4930207 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.5146. Min Act: -0.1700
Data Index: 7859999 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.5146. Min Act: -0.1700
Data Index: 1562896 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.4834. Min Act: -0.1700
Data Index: 2026158 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.4834. Min Act: -0.1700
Data Index: 6349389 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.4521. Min Act: -0.1700
Data Index: 1402051 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.4521. Min Act: -0.1700
Data Index: 4356354 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.4209. Min Act: -0.1700
Data Index: 8619805 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.3896. Min Act: -0.1700
Data Index: 4936599 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.3271. Min Act: -0.1700
Data Index: 275564 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.3584. Min Act: -0.1700
Data Index: 231434 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8584. Min Range: -6.8584
Max Act: 6.3584. Min Act: -0.1700
Data Index: 6821636 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19