Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.6139. Min Act: -0.1700
Data Index: 8427103 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.6139. Min Act: -0.1700
Data Index: 3468629 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.3327. Min Act: -0.1700
Data Index: 4562900 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.3014. Min Act: -0.1700
Data Index: 5098033 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.3014. Min Act: -0.1700
Data Index: 8122603 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.1764. Min Act: -0.1700
Data Index: 2159623 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.1452. Min Act: -0.1700
Data Index: 2646854 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.1452. Min Act: -0.1700
Data Index: 6683530 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.1139. Min Act: -0.1700
Data Index: 2595864 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.1139. Min Act: -0.1700
Data Index: 2060469 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0827. Min Act: -0.1700
Data Index: 3425471 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0827. Min Act: -0.1700
Data Index: 2452762 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0514. Min Act: -0.1700
Data Index: 4727350 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0827. Min Act: -0.1700
Data Index: 5329018 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0514. Min Act: -0.1700
Data Index: 8778557 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0202. Min Act: -0.1700
Data Index: 2684187 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0202. Min Act: -0.1700
Data Index: 1827239 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0202. Min Act: -0.1700
Data Index: 4259071 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6139. Min Range: -5.6139
Max Act: 5.0202. Min Act: -0.1700
Data Index: 2519822 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6139. Min Range: -5.6139
Max Act: 4.9889. Min Act: -0.1700
Data Index: 33573 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19