Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4838. Min Act: -0.1700
Data Index: 316497 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4838. Min Act: -0.1700
Data Index: 7885224 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4676. Min Act: -0.1700
Data Index: 7044322 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4676. Min Act: -0.1700
Data Index: 339141 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4676. Min Act: -0.1700
Data Index: 4965657 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 4178347 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4513. Min Act: -0.1700
Data Index: 6775316 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 6282994 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 6088068 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 5964835 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 3409155 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 1972032 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 7178184 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 7506203 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 1789749 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4188. Min Act: -0.1700
Data Index: 543786 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4025. Min Act: -0.1700
Data Index: 3960978 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4188. Min Act: -0.1700
Data Index: 5021668 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4188. Min Act: -0.1700
Data Index: 362704 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4838. Min Range: -2.4838
Max Act: 2.4351. Min Act: -0.1700
Data Index: 7572239 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19