Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4379 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.6162. Min Act: -0.1700
Data Index: 801011 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.4599. Min Act: -0.1700
Data Index: 638369 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.2724. Min Act: -0.1700
Data Index: 5417973 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.1787. Min Act: -0.1700
Data Index: 2781649 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.1162. Min Act: -0.1700
Data Index: 3306182 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.1474. Min Act: -0.1700
Data Index: 1690862 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.0537. Min Act: -0.1700
Data Index: 5099742 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.0224. Min Act: -0.1700
Data Index: 4868721 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9912. Min Act: -0.1700
Data Index: 2568922 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.0224. Min Act: -0.1700
Data Index: 4840529 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6162. Min Range: -5.6162
Max Act: 5.0224. Min Act: -0.1700
Data Index: 6212681 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9912. Min Act: -0.1700
Data Index: 3435806 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9912. Min Act: -0.1700
Data Index: 8332109 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9599. Min Act: -0.1700
Data Index: 6041728 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9599. Min Act: -0.1700
Data Index: 3812470 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9599. Min Act: -0.1700
Data Index: 4556842 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9599. Min Act: -0.1700
Data Index: 8799005 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9287. Min Act: -0.1700
Data Index: 5954092 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9287. Min Act: -0.1700
Data Index: 5177120 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6162. Min Range: -5.6162
Max Act: 4.9287. Min Act: -0.1700
Data Index: 3649555 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19