Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.6213. Min Act: -0.0001

Data Index: 576521 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1336094 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5476. Min Act: -0.0001

Data Index: 1145189 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5298. Min Act: -0.0001

Data Index: 12117 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5126. Min Act: -0.0001

Data Index: 337553 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4921. Min Act: -0.0001

Data Index: 368460 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1109971 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4847. Min Act: -0.0001

Data Index: 650138 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5802. Min Act: -0.0001

Data Index: 12048 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4179. Min Act: -0.0001

Data Index: 80030 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4951. Min Act: -0.0001

Data Index: 611310 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4747. Min Act: -0.0001

Data Index: 32653 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4830. Min Act: -0.0001

Data Index: 891638 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4526. Min Act: -0.0001

Data Index: 899334 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4807. Min Act: -0.0001

Data Index: 449596 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4644. Min Act: -0.0001

Data Index: 561587 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1057231 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4708. Min Act: -0.0001

Data Index: 417966 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4967. Min Act: -0.0001

Data Index: 202826 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4844. Min Act: -0.0001

Data Index: 134182 (C4 (Web Text))

Max Activating Token Index: 307