Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.3560. Min Act: -0.1700
Data Index: 3301655 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.3560. Min Act: -0.1700
Data Index: 1273981 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.3560. Min Act: -0.1700
Data Index: 6364227 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2933. Min Act: -0.1700
Data Index: 865425 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2462. Min Act: -0.1700
Data Index: 6785445 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2304. Min Act: -0.1700
Data Index: 387639 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2304. Min Act: -0.1700
Data Index: 5666495 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2147. Min Act: -0.1700
Data Index: 8643490 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.2147. Min Act: -0.1700
Data Index: 771532 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1990. Min Act: -0.1700
Data Index: 2901538 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1990. Min Act: -0.1700
Data Index: 6511327 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1833. Min Act: -0.1700
Data Index: 3414782 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1833. Min Act: -0.1700
Data Index: 3057571 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1833. Min Act: -0.1700
Data Index: 4855459 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1675. Min Act: -0.1700
Data Index: 6045110 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1675. Min Act: -0.1700
Data Index: 3234931 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1675. Min Act: -0.1700
Data Index: 4678797 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1360. Min Act: -0.1700
Data Index: 1154405 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1360. Min Act: -0.1700
Data Index: 3613671 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3560. Min Range: -3.3560
Max Act: 3.1360. Min Act: -0.1700
Data Index: 3381208 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19