Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2894 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2469. Min Act: -0.0000

Data Index: 930806 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2638. Min Act: -0.0000

Data Index: 904253 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1095735 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2228. Min Act: -0.0000

Data Index: 267501 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2341. Min Act: -0.0000

Data Index: 924057 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2408. Min Act: -0.0000

Data Index: 16151 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2156. Min Act: -0.0000

Data Index: 579573 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2039. Min Act: -0.0000

Data Index: 972713 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2246. Min Act: -0.0000

Data Index: 211519 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2224. Min Act: -0.0000

Data Index: 273608 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2063. Min Act: -0.0000

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2066. Min Act: -0.0000

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2051. Min Act: -0.0000

Data Index: 307040 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1926. Min Act: -0.0000

Data Index: 796077 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1255847 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1298449 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2093. Min Act: -0.0000

Data Index: 122649 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1935. Min Act: -0.0000

Data Index: 802044 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1936. Min Act: -0.0000

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1860. Min Act: -0.0000

Data Index: 357367 (C4 (Web Text))

Max Activating Token Index: 848