Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4692 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.8677. Min Act: -0.1700
Data Index: 8629007 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.8052. Min Act: -0.1700
Data Index: 6124240 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.6802. Min Act: -0.1700
Data Index: 2667794 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.5552. Min Act: -0.1700
Data Index: 4726566 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.4927. Min Act: -0.1700
Data Index: 4929451 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.5552. Min Act: -0.1700
Data Index: 2390481 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.4927. Min Act: -0.1700
Data Index: 8621423 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.4302. Min Act: -0.1700
Data Index: 6651749 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.3677. Min Act: -0.1700
Data Index: 3755625 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.3677. Min Act: -0.1700
Data Index: 260099 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.3677. Min Act: -0.1700
Data Index: 8421622 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 6778487 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.3052. Min Act: -0.1700
Data Index: 406621 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 6869314 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 3597929 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 2386611 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.2427. Min Act: -0.1700
Data Index: 3661430 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.1802. Min Act: -0.1700
Data Index: 414175 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.1802. Min Act: -0.1700
Data Index: 3505831 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8677. Min Range: -8.8677
Max Act: 8.1802. Min Act: -0.1700
Data Index: 7675389 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19