Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5691 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0000. Min Range: -8.0000
Max Act: 8.0000. Min Act: -0.1700
Data Index: 7845292 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.9062. Min Act: -0.1700
Data Index: 5545682 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.9062. Min Act: -0.1700
Data Index: 6369061 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.8750. Min Act: -0.1700
Data Index: 4575151 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.8125. Min Act: -0.1700
Data Index: 7110433 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.7812. Min Act: -0.1700
Data Index: 6227980 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.7500. Min Act: -0.1700
Data Index: 1403848 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.7187. Min Act: -0.1700
Data Index: 7969230 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.6250. Min Act: -0.1700
Data Index: 4921437 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.6562. Min Act: -0.1700
Data Index: 3177426 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.5937. Min Act: -0.1700
Data Index: 3919863 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.5625. Min Act: -0.1700
Data Index: 7585379 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.5937. Min Act: -0.1700
Data Index: 5873991 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.5625. Min Act: -0.1700
Data Index: 581305 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.5625. Min Act: -0.1700
Data Index: 7058266 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.5312. Min Act: -0.1700
Data Index: 1405766 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.4687. Min Act: -0.1700
Data Index: 4671811 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.4687. Min Act: -0.1700
Data Index: 7389233 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.4687. Min Act: -0.1700
Data Index: 8140910 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0000. Min Range: -8.0000
Max Act: 7.4687. Min Act: -0.1700
Data Index: 3026791 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19