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

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

Neuron 5716 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1174. Min Range: -4.1174

Max Act: 4.1174. Min Act: -0.0000

Data Index: 706973 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 4.1174. Min Range: -4.1174

Max Act: 4.0359. Min Act: -0.0000

Data Index: 1184759 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.2771. Min Act: -0.0000

Data Index: 1263315 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.2879. Min Act: -0.0000

Data Index: 1031571 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.0858. Min Act: -0.0000

Data Index: 825216 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.2672. Min Act: -0.0000

Data Index: 592063 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.7497. Min Act: -0.0000

Data Index: 717855 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.3632. Min Act: -0.0000

Data Index: 509707 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.3975. Min Act: -0.0000

Data Index: 1018587 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.2179. Min Act: -0.0000

Data Index: 1356812 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.4580. Min Act: -0.0000

Data Index: 1269972 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.2504. Min Act: -0.0000

Data Index: 942130 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.1032. Min Act: -0.0000

Data Index: 945421 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.3649. Min Act: -0.0000

Data Index: 51828 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.2428. Min Act: -0.0000

Data Index: 369725 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.0325. Min Act: -0.0000

Data Index: 1054437 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.1872. Min Act: -0.0000

Data Index: 238301 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.1783. Min Act: -0.0000

Data Index: 127826 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 4.1174. Min Range: -4.1174

Max Act: 2.8748. Min Act: -0.0000

Data Index: 172780 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 4.1174. Min Range: -4.1174

Max Act: 3.3509. Min Act: -0.0000

Data Index: 1328926 (C4 (Web Text))

Max Activating Token Index: 847