Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 746 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.4843. Min Act: -0.0001

Data Index: 26577 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.4263. Min Act: -0.0001

Data Index: 30226 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.3325. Min Act: -0.0001

Data Index: 133550 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.1130. Min Act: -0.0001

Data Index: 626994 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.0576. Min Act: -0.0001

Data Index: 1068126 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.0427. Min Act: -0.0001

Data Index: 787460 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.4843. Min Range: -1.4843

Max Act: 1.0480. Min Act: -0.0001

Data Index: 411606 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.9496. Min Act: -0.0001

Data Index: 116446 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.9173. Min Act: -0.0001

Data Index: 478287 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.9454. Min Act: -0.0001

Data Index: 1271825 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.9208. Min Act: -0.0001

Data Index: 695210 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1038793 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.8819. Min Act: -0.0001

Data Index: 857822 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.8516. Min Act: -0.0001

Data Index: 268058 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.8463. Min Act: -0.0001

Data Index: 108289 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.8534. Min Act: -0.0001

Data Index: 773047 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1180632 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.7996. Min Act: -0.0001

Data Index: 52786 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.8001. Min Act: -0.0001

Data Index: 953872 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.4843. Min Range: -1.4843

Max Act: 0.7915. Min Act: -0.0001

Data Index: 189719 (C4 (Web Text))

Max Activating Token Index: 871