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

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

Neuron 3406 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1212. Min Range: -1.1212

Max Act: 1.1212. Min Act: -0.0000

Data Index: 787850 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.1212. Min Range: -1.1212

Max Act: 1.0415. Min Act: -0.0000

Data Index: 955710 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.1212. Min Range: -1.1212

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1058225 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9788. Min Act: -0.0000

Data Index: 42269 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9432. Min Act: 0.0000

Data Index: 72537 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9143. Min Act: -0.0000

Data Index: 233869 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.9483. Min Act: -0.0000

Data Index: 652489 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8939. Min Act: -0.0000

Data Index: 104008 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8537. Min Act: -0.0000

Data Index: 880452 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8794. Min Act: -0.0000

Data Index: 49943 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1168675 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8465. Min Act: -0.0000

Data Index: 284774 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1149017 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8361. Min Act: -0.0000

Data Index: 546440 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.7758. Min Act: -0.0000

Data Index: 507598 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1260353 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8134. Min Act: -0.0000

Data Index: 832040 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8169. Min Act: -0.0000

Data Index: 423705 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8104. Min Act: -0.0000

Data Index: 833974 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.1212. Min Range: -1.1212

Max Act: 0.8016. Min Act: -0.0000

Data Index: 101397 (C4 (Web Text))

Max Activating Token Index: 483