Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2584 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5256. Min Range: -7.5256
Max Act: 7.5256. Min Act: -0.1700
Data Index: 7680887 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5256. Min Range: -7.5256
Max Act: 7.3694. Min Act: -0.1700
Data Index: 6506532 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5256. Min Range: -7.5256
Max Act: 7.2444. Min Act: -0.1700
Data Index: 7668826 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5256. Min Range: -7.5256
Max Act: 7.1819. Min Act: -0.1700
Data Index: 7610156 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5256. Min Range: -7.5256
Max Act: 7.1194. Min Act: -0.1700
Data Index: 3623589 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.9944. Min Act: -0.1700
Data Index: 5318046 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.9006. Min Act: -0.1700
Data Index: 6567322 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.9006. Min Act: -0.1700
Data Index: 4787181 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.8381. Min Act: -0.1700
Data Index: 5467629 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.8069. Min Act: -0.1700
Data Index: 3831461 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.7756. Min Act: -0.1700
Data Index: 6096085 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.7131. Min Act: -0.1700
Data Index: 4472657 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.7444. Min Act: -0.1700
Data Index: 8503921 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.6819. Min Act: -0.1700
Data Index: 1480304 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.7131. Min Act: -0.1700
Data Index: 6953239 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.6506. Min Act: -0.1700
Data Index: 3214345 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7198765 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.6819. Min Act: -0.1700
Data Index: 3995087 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7843755 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5256. Min Range: -7.5256
Max Act: 6.6506. Min Act: -0.1700
Data Index: 8651312 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19