Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.9651. Min Act: -0.1700
Data Index: 1793476 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.9338. Min Act: -0.1700
Data Index: 2671349 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.9338. Min Act: -0.1700
Data Index: 7575187 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8713. Min Act: -0.1700
Data Index: 5986716 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8713. Min Act: -0.1700
Data Index: 3852786 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8713. Min Act: -0.1700
Data Index: 529590 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8713. Min Act: -0.1700
Data Index: 3491572 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8400. Min Act: -0.1700
Data Index: 4152260 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 4652746 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 5169889 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 2328268 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 1735874 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 3854775 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 4454703 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.7462. Min Act: -0.1700
Data Index: 5355073 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.7775. Min Act: -0.1700
Data Index: 5905386 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.7775. Min Act: -0.1700
Data Index: 3755887 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.7775. Min Act: -0.1700
Data Index: 1460047 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.8088. Min Act: -0.1700
Data Index: 375418 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9651. Min Range: -3.9651
Max Act: 3.7462. Min Act: -0.1700
Data Index: 2001216 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19