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

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

Neuron 3618 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2503. Min Act: -0.0000

Data Index: 736875 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2316. Min Act: -0.0000

Data Index: 182963 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2457. Min Act: -0.0000

Data Index: 423835 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1227045 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2221. Min Act: -0.0000

Data Index: 585248 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2278. Min Act: -0.0000

Data Index: 30382 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1351599 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1950. Min Act: -0.0000

Data Index: 501645 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1183077 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1943. Min Act: -0.0000

Data Index: 200030 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1796. Min Act: -0.0000

Data Index: 720593 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2148. Min Act: -0.0000

Data Index: 451282 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1128388 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1835. Min Act: -0.0000

Data Index: 99385 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1027935 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1895. Min Act: -0.0000

Data Index: 746575 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1761. Min Act: -0.0000

Data Index: 116847 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1706. Min Act: -0.0000

Data Index: 90566 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1867. Min Act: -0.0000

Data Index: 938331 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1199984 (C4 (Web Text))

Max Activating Token Index: 412