Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5566 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1420. Min Range: -5.1420
Max Act: 5.1420. Min Act: -0.1700
Data Index: 6104719 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1420. Min Range: -5.1420
Max Act: 5.0170. Min Act: -0.1700
Data Index: 110565 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1420. Min Range: -5.1420
Max Act: 5.0170. Min Act: -0.1700
Data Index: 4030568 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.9857. Min Act: -0.1700
Data Index: 1238441 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.9232. Min Act: -0.1700
Data Index: 3524777 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.9232. Min Act: -0.1700
Data Index: 49756 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.8607. Min Act: -0.1700
Data Index: 8601243 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.8607. Min Act: -0.1700
Data Index: 4177725 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.8607. Min Act: -0.1700
Data Index: 6637454 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.8295. Min Act: -0.1700
Data Index: 8727155 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7982. Min Act: -0.1700
Data Index: 2222449 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7982. Min Act: -0.1700
Data Index: 6841440 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7670. Min Act: -0.1700
Data Index: 5551756 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7982. Min Act: -0.1700
Data Index: 2058330 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7982. Min Act: -0.1700
Data Index: 2576942 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7357. Min Act: -0.1700
Data Index: 1042465 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7357. Min Act: -0.1700
Data Index: 535883 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7045. Min Act: -0.1700
Data Index: 4780231 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4678405 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1420. Min Range: -5.1420
Max Act: 4.7045. Min Act: -0.1700
Data Index: 3602767 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19