Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4019. Min Range: -9.4019
Max Act: 9.4019. Min Act: -0.1700
Data Index: 6613877 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4019. Min Range: -9.4019
Max Act: 9.2769. Min Act: -0.1700
Data Index: 5978812 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4019. Min Range: -9.4019
Max Act: 9.1519. Min Act: -0.1700
Data Index: 4249545 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.9019. Min Act: -0.1700
Data Index: 429329 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.8394. Min Act: -0.1700
Data Index: 7966428 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.8394. Min Act: -0.1700
Data Index: 817638 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.8394. Min Act: -0.1700
Data Index: 4529722 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.7769. Min Act: -0.1700
Data Index: 8110679 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.7769. Min Act: -0.1700
Data Index: 1439912 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.7769. Min Act: -0.1700
Data Index: 4304539 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.6519. Min Act: -0.1700
Data Index: 54768 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.7769. Min Act: -0.1700
Data Index: 5194417 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.6519. Min Act: -0.1700
Data Index: 3382833 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.7144. Min Act: -0.1700
Data Index: 2934581 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.7144. Min Act: -0.1700
Data Index: 2001640 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.5894. Min Act: -0.1700
Data Index: 5801969 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.6519. Min Act: -0.1700
Data Index: 1607652 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.5894. Min Act: -0.1700
Data Index: 221803 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.6519. Min Act: -0.1700
Data Index: 1625929 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4019. Min Range: -9.4019
Max Act: 8.6519. Min Act: -0.1700
Data Index: 5174011 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19