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

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

Neuron 417 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: 4.1886. Min Range: -4.1886

Max Act: 4.1886. Min Act: -0.0000

Data Index: 461459 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.3137. Min Act: -0.0000

Data Index: 967624 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.4658. Min Act: -0.0000

Data Index: 388157 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.2541. Min Act: -0.0000

Data Index: 1245810 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.0002. Min Act: -0.0000

Data Index: 1102345 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.2546. Min Act: -0.0000

Data Index: 887043 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.9351. Min Act: -0.0000

Data Index: 487296 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.9386. Min Act: -0.0000

Data Index: 1216749 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.6593. Min Act: -0.0000

Data Index: 221280 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.0874. Min Act: -0.0000

Data Index: 152848 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.2314. Min Act: -0.0000

Data Index: 424627 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.0242. Min Act: -0.0000

Data Index: 908935 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.0303. Min Act: -0.0000

Data Index: 18909 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.1186. Min Act: -0.0000

Data Index: 542578 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.9829. Min Act: -0.0000

Data Index: 122462 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.9161. Min Act: -0.0000

Data Index: 94363 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.7531. Min Act: -0.0000

Data Index: 194205 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.8990. Min Act: -0.0000

Data Index: 1225986 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 4.1886. Min Range: -4.1886

Max Act: 3.0432. Min Act: -0.0000

Data Index: 35345 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 4.1886. Min Range: -4.1886

Max Act: 2.8516. Min Act: -0.0000

Data Index: 98647 (C4 (Web Text))

Max Activating Token Index: 131