Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0047. Min Range: -2.0047
Max Act: 2.0047. Min Act: -0.1700
Data Index: 4512146 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.9709. Min Act: -0.1700
Data Index: 1477646 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.9539. Min Act: -0.1700
Data Index: 7902724 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.8858. Min Act: -0.1700
Data Index: 6650770 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.8431. Min Act: -0.1700
Data Index: 8323597 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.8259. Min Act: -0.1700
Data Index: 664995 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.8345. Min Act: -0.1700
Data Index: 8561805 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.8173. Min Act: -0.1700
Data Index: 6162702 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.8001. Min Act: -0.1700
Data Index: 3666938 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7915. Min Act: -0.1700
Data Index: 4464936 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7829. Min Act: -0.1700
Data Index: 7329389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7829. Min Act: -0.1700
Data Index: 1710225 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7743. Min Act: -0.1700
Data Index: 2655513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7743. Min Act: -0.1700
Data Index: 2610383 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7743. Min Act: -0.1700
Data Index: 3219396 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7743. Min Act: -0.1700
Data Index: 1537276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7570. Min Act: -0.1700
Data Index: 581997 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7657. Min Act: -0.1700
Data Index: 7857445 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7657. Min Act: -0.1700
Data Index: 3650795 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0047. Min Range: -2.0047
Max Act: 1.7657. Min Act: -0.1700
Data Index: 2878202 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19