Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5127 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.4679. Min Act: -0.1700
Data Index: 759478 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.4054. Min Act: -0.1700
Data Index: 5464873 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.3116. Min Act: -0.1700
Data Index: 759474 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.2803. Min Act: -0.1700
Data Index: 6425424 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1553. Min Act: -0.1700
Data Index: 8671534 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1866. Min Act: -0.1700
Data Index: 1983809 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.2178. Min Act: -0.1700
Data Index: 6235605 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1553. Min Act: -0.1700
Data Index: 3667376 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1553. Min Act: -0.1700
Data Index: 5694109 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1241. Min Act: -0.1700
Data Index: 6747269 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1241. Min Act: -0.1700
Data Index: 4788557 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0928. Min Act: -0.1700
Data Index: 2654156 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.1241. Min Act: -0.1700
Data Index: 7195440 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0928. Min Act: -0.1700
Data Index: 6721840 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0928. Min Act: -0.1700
Data Index: 2817029 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0928. Min Act: -0.1700
Data Index: 4402521 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0616. Min Act: -0.1700
Data Index: 5494895 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0616. Min Act: -0.1700
Data Index: 5001086 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0616. Min Act: -0.1700
Data Index: 6473232 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4679. Min Range: -4.4679
Max Act: 4.0616. Min Act: -0.1700
Data Index: 4473900 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19