Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 6245488 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.5969. Min Act: -0.1700
Data Index: 2529716 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.5032. Min Act: -0.1700
Data Index: 3167599 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.4407. Min Act: -0.1700
Data Index: 3513796 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.4719. Min Act: -0.1700
Data Index: 8322019 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.4719. Min Act: -0.1700
Data Index: 4465792 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.4094. Min Act: -0.1700
Data Index: 831100 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3782. Min Act: -0.1700
Data Index: 5955842 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3782. Min Act: -0.1700
Data Index: 6063771 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3469. Min Act: -0.1700
Data Index: 923396 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3469. Min Act: -0.1700
Data Index: 7264353 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 1509922 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 4591881 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3469. Min Act: -0.1700
Data Index: 1907138 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2844. Min Act: -0.1700
Data Index: 5449259 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2844. Min Act: -0.1700
Data Index: 1940979 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 4044562 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2844. Min Act: -0.1700
Data Index: 6692238 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2844. Min Act: -0.1700
Data Index: 8029725 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2532. Min Act: -0.1700
Data Index: 2223592 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19