Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1361 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.9019. Min Act: -0.1700
Data Index: 2891815 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.8707. Min Act: -0.1700
Data Index: 3417053 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.8394. Min Act: -0.1700
Data Index: 8516991 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.8082. Min Act: -0.1700
Data Index: 5196070 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.7769. Min Act: -0.1700
Data Index: 6280873 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.7457. Min Act: -0.1700
Data Index: 4663185 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6832. Min Act: -0.1700
Data Index: 2433576 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.7144. Min Act: -0.1700
Data Index: 4243656 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.7144. Min Act: -0.1700
Data Index: 2311783 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6832. Min Act: -0.1700
Data Index: 5139609 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6832. Min Act: -0.1700
Data Index: 65755 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6519. Min Act: -0.1700
Data Index: 8232208 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6832. Min Act: -0.1700
Data Index: 830754 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6519. Min Act: -0.1700
Data Index: 654608 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6519. Min Act: -0.1700
Data Index: 4757592 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6519. Min Act: -0.1700
Data Index: 6528870 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6519. Min Act: -0.1700
Data Index: 1699927 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6207. Min Act: -0.1700
Data Index: 301189 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6519. Min Act: -0.1700
Data Index: 1737507 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9019. Min Range: -6.9019
Max Act: 6.6207. Min Act: -0.1700
Data Index: 2401083 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19