Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4677996 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.4019. Min Act: -0.1700
Data Index: 607401 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.3706. Min Act: -0.1700
Data Index: 6147487 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.2769. Min Act: -0.1700
Data Index: 8170655 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.2456. Min Act: -0.1700
Data Index: 1927154 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.1206. Min Act: -0.1700
Data Index: 5310567 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2793169 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.1206. Min Act: -0.1700
Data Index: 577015 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0894. Min Act: -0.1700
Data Index: 305322 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0581. Min Act: -0.1700
Data Index: 2930371 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0269. Min Act: -0.1700
Data Index: 6115168 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0269. Min Act: -0.1700
Data Index: 3798695 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0269. Min Act: -0.1700
Data Index: 1938223 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5269. Min Range: -5.5269
Max Act: 5.0581. Min Act: -0.1700
Data Index: 3165933 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5269. Min Range: -5.5269
Max Act: 4.9956. Min Act: -0.1700
Data Index: 5728749 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5269. Min Range: -5.5269
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1493907 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5269. Min Range: -5.5269
Max Act: 4.9956. Min Act: -0.1700
Data Index: 6709119 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5269. Min Range: -5.5269
Max Act: 4.9956. Min Act: -0.1700
Data Index: 4138221 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5269. Min Range: -5.5269
Max Act: 4.9956. Min Act: -0.1700
Data Index: 6448663 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5269. Min Range: -5.5269
Max Act: 4.9956. Min Act: -0.1700
Data Index: 6382003 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19