Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1041. Min Range: -8.1041
Max Act: 8.1041. Min Act: -0.1700
Data Index: 8523080 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.9791. Min Act: -0.1700
Data Index: 3335908 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.9166. Min Act: -0.1700
Data Index: 3990947 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.5416. Min Act: -0.1700
Data Index: 3195594 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.4791. Min Act: -0.1700
Data Index: 1842527 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.4791. Min Act: -0.1700
Data Index: 2076278 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.4791. Min Act: -0.1700
Data Index: 5510320 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.2291. Min Act: -0.1700
Data Index: 6072562 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.2603. Min Act: -0.1700
Data Index: 3718799 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.2291. Min Act: -0.1700
Data Index: 6072552 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1978. Min Act: -0.1700
Data Index: 7494581 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1978. Min Act: -0.1700
Data Index: 8418569 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1666. Min Act: -0.1700
Data Index: 3938194 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1353. Min Act: -0.1700
Data Index: 5254026 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1041. Min Act: -0.1700
Data Index: 6587303 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1353. Min Act: -0.1700
Data Index: 6003026 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1353. Min Act: -0.1700
Data Index: 5680514 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1041. Min Act: -0.1700
Data Index: 7597680 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1041. Min Act: -0.1700
Data Index: 6459400 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1041. Min Range: -8.1041
Max Act: 7.1041. Min Act: -0.1700
Data Index: 2820108 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19