Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 483 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.4453. Min Act: -0.1700
Data Index: 5646978 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.2890. Min Act: -0.1700
Data Index: 7024048 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.1640. Min Act: -0.1700
Data Index: 1960928 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.0703. Min Act: -0.1700
Data Index: 4944684 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.1015. Min Act: -0.1700
Data Index: 7239391 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.0078. Min Act: -0.1700
Data Index: 7069471 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9453. Min Act: -0.1700
Data Index: 1284829 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9765. Min Act: -0.1700
Data Index: 5801574 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9453. Min Act: -0.1700
Data Index: 3826163 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9140. Min Act: -0.1700
Data Index: 8430919 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9453. Min Act: -0.1700
Data Index: 4931663 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8515. Min Act: -0.1700
Data Index: 6084458 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8828. Min Act: -0.1700
Data Index: 6533660 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8515. Min Act: -0.1700
Data Index: 3833518 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8203. Min Act: -0.1700
Data Index: 4469631 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6410097 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6070884 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 3276907 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7890. Min Act: -0.1700
Data Index: 5759728 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 1542548 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19