Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.5725. Min Act: -0.1700
Data Index: 349011 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.5413. Min Act: -0.1700
Data Index: 5946993 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4788. Min Act: -0.1700
Data Index: 4673357 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4788. Min Act: -0.1700
Data Index: 2561523 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4788. Min Act: -0.1700
Data Index: 3662221 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4163. Min Act: -0.1700
Data Index: 954942 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4163. Min Act: -0.1700
Data Index: 3347802 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4163. Min Act: -0.1700
Data Index: 5283845 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3850. Min Act: -0.1700
Data Index: 6111128 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4163. Min Act: -0.1700
Data Index: 807416 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4163. Min Act: -0.1700
Data Index: 1652283 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.4163. Min Act: -0.1700
Data Index: 886688 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3850. Min Act: -0.1700
Data Index: 7127351 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3850. Min Act: -0.1700
Data Index: 6505345 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3850. Min Act: -0.1700
Data Index: 6461726 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3538. Min Act: -0.1700
Data Index: 4221162 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3538. Min Act: -0.1700
Data Index: 1651246 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3538. Min Act: -0.1700
Data Index: 1508025 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3538. Min Act: -0.1700
Data Index: 3854714 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5725. Min Range: -4.5725
Max Act: 4.3538. Min Act: -0.1700
Data Index: 5943112 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19