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

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

Neuron 2816 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.8423. Min Act: -0.0001

Data Index: 80577 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6857. Min Act: -0.0001

Data Index: 153948 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1294085 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6476. Min Act: -0.0001

Data Index: 678244 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6489. Min Act: -0.0001

Data Index: 287160 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6386. Min Act: -0.0001

Data Index: 689816 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6081. Min Act: -0.0001

Data Index: 231399 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6330. Min Act: -0.0001

Data Index: 1126970 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6084. Min Act: -0.0001

Data Index: 1117029 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6202. Min Act: -0.0001

Data Index: 120130 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6068. Min Act: -0.0001

Data Index: 273491 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6073. Min Act: -0.0001

Data Index: 170359 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6089. Min Act: -0.0001

Data Index: 25331 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5657. Min Act: -0.0001

Data Index: 944289 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5756. Min Act: -0.0000

Data Index: 904200 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5707. Min Act: -0.0001

Data Index: 237594 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1122756 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1094666 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5567. Min Act: -0.0000

Data Index: 973054 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1120985 (C4 (Web Text))

Max Activating Token Index: 613