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

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

Neuron 3783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.9067. Min Act: -0.0000

Data Index: 457087 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7699. Min Act: -0.0000

Data Index: 237120 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1251291 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7190. Min Act: -0.0000

Data Index: 521200 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7221. Min Act: -0.0000

Data Index: 865462 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6330. Min Act: 0.0000

Data Index: 1031309 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6136. Min Act: -0.0000

Data Index: 179568 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6094. Min Act: -0.0000

Data Index: 510408 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1209488 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5738. Min Act: -0.0000

Data Index: 876074 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5720. Min Act: -0.0000

Data Index: 979088 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5242. Min Act: -0.0000

Data Index: 803272 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1177173 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5248. Min Act: -0.0000

Data Index: 615911 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5172. Min Act: -0.0000

Data Index: 14471 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.4823. Min Act: -0.0000

Data Index: 761999 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1190811 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1051402 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1039198 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.4854. Min Act: -0.0000

Data Index: 305660 (C4 (Web Text))

Max Activating Token Index: 757