Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1213. Min Range: -9.1213
Max Act: 9.1213. Min Act: -0.1700
Data Index: 4978017 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.8713. Min Act: -0.1700
Data Index: 3656789 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.7463. Min Act: -0.1700
Data Index: 1303494 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.6838. Min Act: -0.1700
Data Index: 3331382 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.6213. Min Act: -0.1700
Data Index: 4778197 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.5588. Min Act: -0.1700
Data Index: 8501578 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.4338. Min Act: -0.1700
Data Index: 4959923 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.4338. Min Act: -0.1700
Data Index: 3347527 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.4338. Min Act: -0.1700
Data Index: 1363366 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3713. Min Act: -0.1700
Data Index: 3643362 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3713. Min Act: -0.1700
Data Index: 278942 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3088. Min Act: -0.1700
Data Index: 821442 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3088. Min Act: -0.1700
Data Index: 3080862 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3088. Min Act: -0.1700
Data Index: 3375908 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3713. Min Act: -0.1700
Data Index: 5447583 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.3088. Min Act: -0.1700
Data Index: 5769761 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.2463. Min Act: -0.1700
Data Index: 3988529 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.2463. Min Act: -0.1700
Data Index: 5770072 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.2463. Min Act: -0.1700
Data Index: 1659440 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1213. Min Range: -9.1213
Max Act: 8.1838. Min Act: -0.1700
Data Index: 3102090 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19