Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1993 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.9733. Min Act: -0.1700
Data Index: 2687010 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.9108. Min Act: -0.1700
Data Index: 453272 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.8483. Min Act: -0.1700
Data Index: 4728856 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.7858. Min Act: -0.1700
Data Index: 8124600 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.7233. Min Act: -0.1700
Data Index: 4940008 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.7233. Min Act: -0.1700
Data Index: 1511495 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.7233. Min Act: -0.1700
Data Index: 1416728 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.6608. Min Act: -0.1700
Data Index: 915289 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.6608. Min Act: -0.1700
Data Index: 6573934 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.5983. Min Act: -0.1700
Data Index: 3489320 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.5358. Min Act: -0.1700
Data Index: 7191410 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.5358. Min Act: -0.1700
Data Index: 5362971 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.5358. Min Act: -0.1700
Data Index: 5274350 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.5358. Min Act: -0.1700
Data Index: 6136475 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 7003816 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 8020769 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 4417694 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 3997079 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 4306345 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9733. Min Range: -8.9733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 5805023 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19