Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3242 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.7268. Min Act: -0.0001

Data Index: 217662 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6772. Min Act: -0.0001

Data Index: 880102 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6169. Min Act: -0.0001

Data Index: 1014479 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1139013 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5863. Min Act: -0.0001

Data Index: 370614 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6097. Min Act: -0.0001

Data Index: 1213432 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6297. Min Act: -0.0001

Data Index: 619784 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6195. Min Act: -0.0001

Data Index: 730994 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6174. Min Act: -0.0001

Data Index: 1181188 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5925. Min Act: -0.0001

Data Index: 285828 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5898. Min Act: -0.0001

Data Index: 324913 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5363. Min Act: -0.0001

Data Index: 1357300 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5370. Min Act: -0.0001

Data Index: 27604 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5635. Min Act: -0.0001

Data Index: 766867 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5198. Min Act: -0.0001

Data Index: 730643 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5492. Min Act: -0.0001

Data Index: 846812 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5691. Min Act: -0.0001

Data Index: 411008 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1282708 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5997. Min Act: -0.0001

Data Index: 40904 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5395. Min Act: -0.0001

Data Index: 1255724 (C4 (Web Text))

Max Activating Token Index: 193