Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.1264. Min Act: -0.1700
Data Index: 480921 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.1577. Min Act: -0.1700
Data Index: 38233 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0952. Min Act: -0.1700
Data Index: 2851337 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0952. Min Act: -0.1700
Data Index: 3922741 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0952. Min Act: -0.1700
Data Index: 1282993 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0014. Min Act: -0.1700
Data Index: 8399302 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0327. Min Act: -0.1700
Data Index: 7196929 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0014. Min Act: -0.1700
Data Index: 6471224 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1577. Min Range: -6.1577
Max Act: 6.0014. Min Act: -0.1700
Data Index: 5382439 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9702. Min Act: -0.1700
Data Index: 4117584 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9702. Min Act: -0.1700
Data Index: 3718090 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9702. Min Act: -0.1700
Data Index: 3597132 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9702. Min Act: -0.1700
Data Index: 978261 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9389. Min Act: -0.1700
Data Index: 810297 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.8764. Min Act: -0.1700
Data Index: 6402452 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9389. Min Act: -0.1700
Data Index: 1891286 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9077. Min Act: -0.1700
Data Index: 7969917 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9077. Min Act: -0.1700
Data Index: 5881367 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9077. Min Act: -0.1700
Data Index: 4661990 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1577. Min Range: -6.1577
Max Act: 5.9077. Min Act: -0.1700
Data Index: 587758 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19