Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3197. Min Range: -5.3197
Max Act: 5.3197. Min Act: -0.1700
Data Index: 4648166 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3197. Min Range: -5.3197
Max Act: 5.1010. Min Act: -0.1700
Data Index: 886666 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3197. Min Range: -5.3197
Max Act: 5.0697. Min Act: -0.1700
Data Index: 7142123 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3197. Min Range: -5.3197
Max Act: 5.0385. Min Act: -0.1700
Data Index: 2276375 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3197. Min Range: -5.3197
Max Act: 5.0072. Min Act: -0.1700
Data Index: 8739641 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3197. Min Range: -5.3197
Max Act: 5.0072. Min Act: -0.1700
Data Index: 5208832 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.9760. Min Act: -0.1700
Data Index: 4339364 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.9135. Min Act: -0.1700
Data Index: 1734269 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.9135. Min Act: -0.1700
Data Index: 617528 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8822. Min Act: -0.1700
Data Index: 8351966 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8510. Min Act: -0.1700
Data Index: 5093027 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8822. Min Act: -0.1700
Data Index: 2277727 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8510. Min Act: -0.1700
Data Index: 7954421 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8510. Min Act: -0.1700
Data Index: 3578425 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8822. Min Act: -0.1700
Data Index: 1947624 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8197. Min Act: -0.1700
Data Index: 8457508 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8197. Min Act: -0.1700
Data Index: 3068106 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8510. Min Act: -0.1700
Data Index: 4214603 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8197. Min Act: -0.1700
Data Index: 6524838 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3197. Min Range: -5.3197
Max Act: 4.8197. Min Act: -0.1700
Data Index: 5352143 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19