Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 586 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.2612. Min Act: -0.1700
Data Index: 3449529 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.2612. Min Act: -0.1700
Data Index: 3811440 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.2299. Min Act: -0.1700
Data Index: 4380602 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1987. Min Act: -0.1700
Data Index: 4203645 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1674. Min Act: -0.1700
Data Index: 6177840 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1987. Min Act: -0.1700
Data Index: 941449 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1674. Min Act: -0.1700
Data Index: 2648724 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1049. Min Act: -0.1700
Data Index: 4641818 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1674. Min Act: -0.1700
Data Index: 8363717 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1674. Min Act: -0.1700
Data Index: 6909637 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1362. Min Act: -0.1700
Data Index: 2593226 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1362. Min Act: -0.1700
Data Index: 4356490 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0737. Min Act: -0.1700
Data Index: 7328430 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0737. Min Act: -0.1700
Data Index: 2522843 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1362. Min Act: -0.1700
Data Index: 2443028 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1049. Min Act: -0.1700
Data Index: 3893882 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1049. Min Act: -0.1700
Data Index: 7306852 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0737. Min Act: -0.1700
Data Index: 4340167 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0424. Min Act: -0.1700
Data Index: 3233122 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0424. Min Act: -0.1700
Data Index: 699266 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19