Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4030. Min Range: -8.4030
Max Act: 8.4030. Min Act: -0.1700
Data Index: 1373550 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.8717. Min Act: -0.1700
Data Index: 7414235 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.8092. Min Act: -0.1700
Data Index: 2385172 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.7155. Min Act: -0.1700
Data Index: 5902023 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.6842. Min Act: -0.1700
Data Index: 7599014 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.6842. Min Act: -0.1700
Data Index: 6345471 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.6530. Min Act: -0.1700
Data Index: 4719828 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.5905. Min Act: -0.1700
Data Index: 5459851 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.5592. Min Act: -0.1700
Data Index: 2236839 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.5592. Min Act: -0.1700
Data Index: 2502895 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.5592. Min Act: -0.1700
Data Index: 1746770 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.5280. Min Act: -0.1700
Data Index: 5522367 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4967. Min Act: -0.1700
Data Index: 5511984 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4967. Min Act: -0.1700
Data Index: 8719056 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4967. Min Act: -0.1700
Data Index: 5292344 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4655. Min Act: -0.1700
Data Index: 7342932 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4342. Min Act: -0.1700
Data Index: 6225963 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4342. Min Act: -0.1700
Data Index: 480193 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4030. Min Act: -0.1700
Data Index: 6175334 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4030. Min Range: -8.4030
Max Act: 7.4030. Min Act: -0.1700
Data Index: 648958 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19