Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2724 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.9159. Min Act: -0.0000

Data Index: 596374 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.7167. Min Act: -0.0000

Data Index: 431303 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.2924. Min Act: -0.0000

Data Index: 1218142 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.4649. Min Act: -0.0000

Data Index: 272668 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.5779. Min Act: -0.0000

Data Index: 1125625 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.2199. Min Act: -0.0000

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1034984 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.1136. Min Act: -0.0000

Data Index: 839593 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 2.9159. Min Range: -2.9159

Max Act: 2.0692. Min Act: -0.0000

Data Index: 439331 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.8853. Min Act: -0.0000

Data Index: 1103976 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.9761. Min Act: -0.0000

Data Index: 67955 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.9620. Min Act: -0.0000

Data Index: 914120 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.8665. Min Act: -0.0000

Data Index: 20640 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.9457. Min Act: -0.0000

Data Index: 164065 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.9356. Min Act: -0.0000

Data Index: 16579 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.8709. Min Act: -0.0000

Data Index: 1059901 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.8502. Min Act: -0.0000

Data Index: 1182886 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.8252. Min Act: -0.0000

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.6413. Min Act: -0.0000

Data Index: 171308 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 2.9159. Min Range: -2.9159

Max Act: 1.7996. Min Act: -0.0000

Data Index: 86875 (C4 (Web Text))

Max Activating Token Index: 292