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

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

Neuron 3061 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: 3.1547. Min Range: -3.1547

Max Act: 3.1547. Min Act: -0.0000

Data Index: 293008 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.9846. Min Act: -0.0000

Data Index: 639655 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.6703. Min Act: -0.0000

Data Index: 584781 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.9483. Min Act: -0.0000

Data Index: 747606 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.6233. Min Act: -0.0000

Data Index: 347676 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.3407. Min Act: -0.0000

Data Index: 294778 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.4551. Min Act: -0.0000

Data Index: 1330121 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.4514. Min Act: -0.0000

Data Index: 320848 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.4660. Min Act: -0.0000

Data Index: 451443 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.3158. Min Act: -0.0000

Data Index: 1304841 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1314737 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.3260. Min Act: -0.0000

Data Index: 130677 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.1815. Min Act: -0.0000

Data Index: 1101473 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.4061. Min Act: -0.0000

Data Index: 450875 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.1182. Min Act: -0.0000

Data Index: 620959 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.2409. Min Act: -0.0000

Data Index: 337429 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.1226. Min Act: -0.0000

Data Index: 576636 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.2236. Min Act: -0.0000

Data Index: 1015082 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.1998. Min Act: -0.0000

Data Index: 107691 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 3.1547. Min Range: -3.1547

Max Act: 2.2997. Min Act: -0.0000

Data Index: 1209048 (C4 (Web Text))

Max Activating Token Index: 999