Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5666. Min Range: -5.5666
Max Act: 5.5666. Min Act: -0.1700
Data Index: 3203750 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5666. Min Range: -5.5666
Max Act: 5.1916. Min Act: -0.1700
Data Index: 4443352 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5666. Min Range: -5.5666
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6512393 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5666. Min Range: -5.5666
Max Act: 5.0354. Min Act: -0.1700
Data Index: 1855625 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5666. Min Range: -5.5666
Max Act: 5.0666. Min Act: -0.1700
Data Index: 4692347 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5666. Min Range: -5.5666
Max Act: 5.0354. Min Act: -0.1700
Data Index: 2386220 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9729. Min Act: -0.1700
Data Index: 4538051 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9729. Min Act: -0.1700
Data Index: 4538057 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9729. Min Act: -0.1700
Data Index: 3302732 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2263506 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9416. Min Act: -0.1700
Data Index: 5591668 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 1223717 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 2077034 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 6365340 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 203033 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 6512396 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 7690982 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 5106152 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 2163487 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5666. Min Range: -5.5666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 6341680 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19