Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.4200. Min Act: -0.1700
Data Index: 6186572 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.3575. Min Act: -0.1700
Data Index: 6821535 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.2950. Min Act: -0.1700
Data Index: 8249981 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.2638. Min Act: -0.1700
Data Index: 6736485 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.1700. Min Act: -0.1700
Data Index: 5964587 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.1388. Min Act: -0.1700
Data Index: 798224 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.0763. Min Act: -0.1700
Data Index: 3296420 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.0450. Min Act: -0.1700
Data Index: 3189529 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4200. Min Range: -6.4200
Max Act: 6.0138. Min Act: -0.1700
Data Index: 5260330 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.9825. Min Act: -0.1700
Data Index: 2535744 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.9200. Min Act: -0.1700
Data Index: 3820391 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8888. Min Act: -0.1700
Data Index: 4670478 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8888. Min Act: -0.1700
Data Index: 8769475 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8575. Min Act: -0.1700
Data Index: 3441072 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8888. Min Act: -0.1700
Data Index: 2638552 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8575. Min Act: -0.1700
Data Index: 5928642 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8575. Min Act: -0.1700
Data Index: 3744154 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8575. Min Act: -0.1700
Data Index: 8488146 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8575. Min Act: -0.1700
Data Index: 7054899 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4200. Min Range: -6.4200
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3490315 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19