Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4935 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.1169. Min Act: -0.1700
Data Index: 8708817 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.0856. Min Act: -0.1700
Data Index: 7249824 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.0856. Min Act: -0.1700
Data Index: 5175511 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.0544. Min Act: -0.1700
Data Index: 447436 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.0544. Min Act: -0.1700
Data Index: 6240517 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.9606. Min Act: -0.1700
Data Index: 7045994 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.9294. Min Act: -0.1700
Data Index: 4429378 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.9294. Min Act: -0.1700
Data Index: 55238 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 6231522 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8981. Min Act: -0.1700
Data Index: 33368 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8981. Min Act: -0.1700
Data Index: 1370633 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8981. Min Act: -0.1700
Data Index: 2936339 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 6243263 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8356. Min Act: -0.1700
Data Index: 8269783 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 7454139 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8981. Min Act: -0.1700
Data Index: 656790 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 307748 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 7999473 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 4399149 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8356. Min Act: -0.1700
Data Index: 6658954 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19