Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.5638. Min Act: -0.1700
Data Index: 7162583 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.5326. Min Act: -0.1700
Data Index: 7978028 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.4701. Min Act: -0.1700
Data Index: 7626563 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.4388. Min Act: -0.1700
Data Index: 3056435 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.4388. Min Act: -0.1700
Data Index: 8396736 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.3763. Min Act: -0.1700
Data Index: 1778302 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.3451. Min Act: -0.1700
Data Index: 6771310 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2826. Min Act: -0.1700
Data Index: 1802045 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 8093366 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2513. Min Act: -0.1700
Data Index: 3240773 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2513. Min Act: -0.1700
Data Index: 5366057 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2513. Min Act: -0.1700
Data Index: 3289646 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 807010 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 4667961 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 3523256 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.1888. Min Act: -0.1700
Data Index: 4712768 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 384849 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 5178857 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 2293316 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5638. Min Range: -4.5638
Max Act: 4.2201. Min Act: -0.1700
Data Index: 3284777 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19