Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1877 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2457. Min Range: -6.2457
Max Act: 6.2457. Min Act: -0.1700
Data Index: 1278403 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2457. Min Range: -6.2457
Max Act: 6.1520. Min Act: -0.1700
Data Index: 5391521 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2457. Min Range: -6.2457
Max Act: 6.1520. Min Act: -0.1700
Data Index: 937019 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2457. Min Range: -6.2457
Max Act: 6.0582. Min Act: -0.1700
Data Index: 6315245 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9957. Min Act: -0.1700
Data Index: 5798632 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9957. Min Act: -0.1700
Data Index: 324949 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2457. Min Range: -6.2457
Max Act: 6.0270. Min Act: -0.1700
Data Index: 131823 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9957. Min Act: -0.1700
Data Index: 7217458 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9957. Min Act: -0.1700
Data Index: 4401426 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9957. Min Act: -0.1700
Data Index: 8059828 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9957. Min Act: -0.1700
Data Index: 4704042 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9332. Min Act: -0.1700
Data Index: 5716190 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9645. Min Act: -0.1700
Data Index: 8061183 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9332. Min Act: -0.1700
Data Index: 77209 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9645. Min Act: -0.1700
Data Index: 613459 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9645. Min Act: -0.1700
Data Index: 1732582 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9332. Min Act: -0.1700
Data Index: 3824723 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9332. Min Act: -0.1700
Data Index: 4235947 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9332. Min Act: -0.1700
Data Index: 7410821 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2457. Min Range: -6.2457
Max Act: 5.9332. Min Act: -0.1700
Data Index: 3341578 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19