Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1494 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.8623. Min Act: -0.1700
Data Index: 72322 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.7998. Min Act: -0.1700
Data Index: 673172 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.7373. Min Act: -0.1700
Data Index: 1801232 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.7685. Min Act: -0.1700
Data Index: 4321555 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.7373. Min Act: -0.1700
Data Index: 7098111 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.6748. Min Act: -0.1700
Data Index: 20561 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.6748. Min Act: -0.1700
Data Index: 956617 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.6123. Min Act: -0.1700
Data Index: 177014 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5498. Min Act: -0.1700
Data Index: 642187 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5498. Min Act: -0.1700
Data Index: 5212069 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5810. Min Act: -0.1700
Data Index: 5612942 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5498. Min Act: -0.1700
Data Index: 265247 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5185. Min Act: -0.1700
Data Index: 2977372 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5185. Min Act: -0.1700
Data Index: 3118385 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.4873. Min Act: -0.1700
Data Index: 472807 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.5498. Min Act: -0.1700
Data Index: 6903465 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.4560. Min Act: -0.1700
Data Index: 4921979 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.4560. Min Act: -0.1700
Data Index: 5134648 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.4248. Min Act: -0.1700
Data Index: 4240563 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8623. Min Range: -4.8623
Max Act: 4.4248. Min Act: -0.1700
Data Index: 5105704 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19