Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4945 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.6638. Min Act: -0.1700
Data Index: 8457494 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.6013. Min Act: -0.1700
Data Index: 5915409 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.5075. Min Act: -0.1700
Data Index: 415009 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.4450. Min Act: -0.1700
Data Index: 5132243 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.4138. Min Act: -0.1700
Data Index: 4025351 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.3825. Min Act: -0.1700
Data Index: 2852242 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.3513. Min Act: -0.1700
Data Index: 875855 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.3513. Min Act: -0.1700
Data Index: 6284261 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.3513. Min Act: -0.1700
Data Index: 5673552 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.3200. Min Act: -0.1700
Data Index: 7444074 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.3200. Min Act: -0.1700
Data Index: 2939057 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4810781 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2888. Min Act: -0.1700
Data Index: 6387501 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2575. Min Act: -0.1700
Data Index: 7513562 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2263. Min Act: -0.1700
Data Index: 657884 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2575. Min Act: -0.1700
Data Index: 4584500 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2263. Min Act: -0.1700
Data Index: 6581857 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2263. Min Act: -0.1700
Data Index: 6649848 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.2263. Min Act: -0.1700
Data Index: 4445588 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6638. Min Range: -5.6638
Max Act: 5.1950. Min Act: -0.1700
Data Index: 5718029 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19