Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 665 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2892. Min Range: -7.2892
Max Act: 7.2892. Min Act: -0.1700
Data Index: 7447034 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2892. Min Range: -7.2892
Max Act: 7.0392. Min Act: -0.1700
Data Index: 3156430 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.7892. Min Act: -0.1700
Data Index: 3059286 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.6642. Min Act: -0.1700
Data Index: 534988 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.6329. Min Act: -0.1700
Data Index: 698827 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.4767. Min Act: -0.1700
Data Index: 3497428 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.5079. Min Act: -0.1700
Data Index: 7843750 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.5079. Min Act: -0.1700
Data Index: 3274415 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.4767. Min Act: -0.1700
Data Index: 8132406 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.4454. Min Act: -0.1700
Data Index: 3603211 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.4142. Min Act: -0.1700
Data Index: 2068595 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.4454. Min Act: -0.1700
Data Index: 7278642 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.4142. Min Act: -0.1700
Data Index: 6170650 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3829. Min Act: -0.1700
Data Index: 212790 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3829. Min Act: -0.1700
Data Index: 4198760 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7034693 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3204. Min Act: -0.1700
Data Index: 6394563 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3204. Min Act: -0.1700
Data Index: 3150780 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3204. Min Act: -0.1700
Data Index: 7907191 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2892. Min Range: -7.2892
Max Act: 6.3204. Min Act: -0.1700
Data Index: 7413741 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19