Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.7637. Min Act: -0.1700
Data Index: 3340148 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 331051 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.7011. Min Act: -0.1698
Data Index: 6777 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1695
Data Index: 1175012 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 4381326 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 2999641 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 5924247 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 6330454 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 7004706 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6698. Min Act: -0.1700
Data Index: 8559959 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6385. Min Act: -0.1700
Data Index: 3228054 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6385. Min Act: -0.1700
Data Index: 8650506 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6385. Min Act: -0.1700
Data Index: 2367830 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6385. Min Act: -0.1700
Data Index: 2160318 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6385. Min Act: -0.1700
Data Index: 8017432 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1950439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1689607 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6385. Min Act: -0.1700
Data Index: 1416638 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6072. Min Act: -0.1700
Data Index: 857369 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7637. Min Range: -3.7637
Max Act: 3.6072. Min Act: -0.1700
Data Index: 267632 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19