Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5419 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.3866. Min Act: -0.1700
Data Index: 7777550 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.2303. Min Act: -0.1700
Data Index: 1533222 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.1678. Min Act: -0.1700
Data Index: 2996621 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.1366. Min Act: -0.1700
Data Index: 4398988 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.1366. Min Act: -0.1700
Data Index: 6875465 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.1366. Min Act: -0.1700
Data Index: 606119 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.1053. Min Act: -0.1700
Data Index: 595109 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0741. Min Act: -0.1700
Data Index: 1767129 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0741. Min Act: -0.1700
Data Index: 492622 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0741. Min Act: -0.1700
Data Index: 6500408 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0428. Min Act: -0.1700
Data Index: 2328808 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0116. Min Act: -0.1700
Data Index: 3191829 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0428. Min Act: -0.1700
Data Index: 4688355 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.0116. Min Act: -0.1700
Data Index: 7518406 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.9803. Min Act: -0.1700
Data Index: 6021356 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.9803. Min Act: -0.1700
Data Index: 1253096 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.9491. Min Act: -0.1700
Data Index: 1813701 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.9178. Min Act: -0.1700
Data Index: 2888733 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.9178. Min Act: -0.1700
Data Index: 8735883 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.8866. Min Act: -0.1700
Data Index: 1832696 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19