Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1716 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.4927. Min Act: -0.1700
Data Index: 6714164 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.4302. Min Act: -0.1700
Data Index: 4607151 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.3990. Min Act: -0.1700
Data Index: 906406 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.3052. Min Act: -0.1700
Data Index: 7221198 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.3052. Min Act: -0.1700
Data Index: 4752931 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2740. Min Act: -0.1700
Data Index: 5403509 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.3052. Min Act: -0.1700
Data Index: 4210461 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2740. Min Act: -0.1700
Data Index: 7153485 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2740. Min Act: -0.1700
Data Index: 3546123 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2740. Min Act: -0.1700
Data Index: 669656 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2427. Min Act: -0.1700
Data Index: 2694571 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2740. Min Act: -0.1700
Data Index: 736753 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.3052. Min Act: -0.1700
Data Index: 4184556 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2740. Min Act: -0.1700
Data Index: 7028477 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2427. Min Act: -0.1700
Data Index: 5081160 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2427. Min Act: -0.1700
Data Index: 1394879 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2427. Min Act: -0.1700
Data Index: 3031422 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.2115. Min Act: -0.1700
Data Index: 3482305 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.1802. Min Act: -0.1700
Data Index: 2488443 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4927. Min Range: -5.4927
Max Act: 5.1802. Min Act: -0.1700
Data Index: 4568376 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19