Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 81 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1284. Min Range: -7.1284
Max Act: 7.1284. Min Act: -0.1700
Data Index: 2841767 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1284. Min Range: -7.1284
Max Act: 7.0659. Min Act: -0.1700
Data Index: 3504021 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1284. Min Range: -7.1284
Max Act: 7.0346. Min Act: -0.1700
Data Index: 5167279 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1284. Min Range: -7.1284
Max Act: 7.0346. Min Act: -0.1700
Data Index: 6691677 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1284. Min Range: -7.1284
Max Act: 7.0034. Min Act: -0.1700
Data Index: 620585 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.9409. Min Act: -0.1700
Data Index: 7686947 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.9409. Min Act: -0.1700
Data Index: 4546298 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.9409. Min Act: -0.1700
Data Index: 7114581 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.9409. Min Act: -0.1700
Data Index: 3243749 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.9096. Min Act: -0.1700
Data Index: 8582436 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.9096. Min Act: -0.1700
Data Index: 3766149 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7846. Min Act: -0.1700
Data Index: 3958023 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7846. Min Act: -0.1700
Data Index: 3221950 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7846. Min Act: -0.1700
Data Index: 1865547 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7846. Min Act: -0.1700
Data Index: 5662953 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7846. Min Act: -0.1700
Data Index: 6758735 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7534. Min Act: -0.1700
Data Index: 2091597 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7534. Min Act: -0.1700
Data Index: 5742007 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7221. Min Act: -0.1700
Data Index: 2969213 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1284. Min Range: -7.1284
Max Act: 6.7221. Min Act: -0.1700
Data Index: 8333791 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19