Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0996. Min Range: -6.0996
Max Act: 6.0996. Min Act: -0.1700
Data Index: 320273 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.8809. Min Act: -0.1700
Data Index: 2426079 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.8496. Min Act: -0.1700
Data Index: 7924945 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.6309. Min Act: -0.1700
Data Index: 4737805 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.6309. Min Act: -0.1700
Data Index: 3844997 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.6621. Min Act: -0.1700
Data Index: 1173058 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.6309. Min Act: -0.1700
Data Index: 5957484 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.6309. Min Act: -0.1700
Data Index: 7276622 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5996. Min Act: -0.1700
Data Index: 1999687 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5996. Min Act: -0.1700
Data Index: 3845001 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.6309. Min Act: -0.1700
Data Index: 8340561 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5371. Min Act: -0.1700
Data Index: 3015883 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5371. Min Act: -0.1700
Data Index: 1061403 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5684. Min Act: -0.1700
Data Index: 6020444 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5371. Min Act: -0.1700
Data Index: 3961898 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5371. Min Act: -0.1700
Data Index: 4067159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5059. Min Act: -0.1700
Data Index: 1159386 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.4746. Min Act: -0.1700
Data Index: 3057025 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.5059. Min Act: -0.1700
Data Index: 8060968 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0996. Min Range: -6.0996
Max Act: 5.4746. Min Act: -0.1700
Data Index: 6542105 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19