Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0475. Min Range: -9.0475
Max Act: 9.0475. Min Act: -0.1700
Data Index: 5363185 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.9225. Min Act: -0.1700
Data Index: 144125 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.9225. Min Act: -0.1700
Data Index: 1752177 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.8600. Min Act: -0.1700
Data Index: 6893307 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.7975. Min Act: -0.1700
Data Index: 8079088 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.6725. Min Act: -0.1700
Data Index: 2828185 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.6725. Min Act: -0.1700
Data Index: 6083742 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.5475. Min Act: -0.1700
Data Index: 3317530 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.6100. Min Act: -0.1700
Data Index: 8493806 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.6100. Min Act: -0.1700
Data Index: 4199544 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.5475. Min Act: -0.1700
Data Index: 5994728 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.4225. Min Act: -0.1700
Data Index: 4431512 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.4225. Min Act: -0.1700
Data Index: 7052480 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.4225. Min Act: -0.1700
Data Index: 7907415 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.4225. Min Act: -0.1700
Data Index: 1567285 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.3600. Min Act: -0.1700
Data Index: 292067 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.3600. Min Act: -0.1700
Data Index: 2122555 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.3600. Min Act: -0.1700
Data Index: 7372550 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.3600. Min Act: -0.1700
Data Index: 5373758 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0475. Min Range: -9.0475
Max Act: 8.2975. Min Act: -0.1700
Data Index: 977486 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19