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

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

Neuron 6045 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.2408. Min Act: -0.0000

Data Index: 477219 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.1019. Min Act: -0.0000

Data Index: 964040 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.1205. Min Act: -0.0000

Data Index: 1193007 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.0251. Min Act: -0.0000

Data Index: 827910 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.0152. Min Act: -0.0000

Data Index: 570119 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.0702. Min Act: -0.0000

Data Index: 840285 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.2408. Min Range: -1.2408

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1099133 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.9599. Min Act: -0.0000

Data Index: 681340 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1272470 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1128030 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1250473 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.9361. Min Act: -0.0000

Data Index: 57305 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.8638. Min Act: -0.0000

Data Index: 49709 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.8144. Min Act: -0.0000

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.7975. Min Act: -0.0000

Data Index: 626134 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1355318 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.7076. Min Act: -0.0000

Data Index: 781428 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.6952. Min Act: -0.0000

Data Index: 631030 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.7315. Min Act: -0.0000

Data Index: 509274 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.2408. Min Range: -1.2408

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1135257 (C4 (Web Text))

Max Activating Token Index: 146