Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1682 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3929. Min Act: -0.0004

Data Index: 380521 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3965. Min Act: -0.0003

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3287. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #3

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3045. Min Act: -0.0003

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2682. Min Act: -0.0003

Data Index: 1090252 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2759. Min Act: -0.0003

Data Index: 254973 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2588. Min Act: -0.0003

Data Index: 1313376 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2553. Min Act: -0.0003

Data Index: 1575383 (Python Code)

Max Activating Token Index: 868

Text #8

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2350. Min Act: -0.0003

Data Index: 362588 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2541. Min Act: -0.0003

Data Index: 617587 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2267. Min Act: -0.0003

Data Index: 275940 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2337. Min Act: -0.0004

Data Index: 186053 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2187. Min Act: -0.0003

Data Index: 1356092 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2265. Min Act: -0.0003

Data Index: 937574 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2202. Min Act: -0.0003

Data Index: 73268 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2133. Min Act: -0.0003

Data Index: 1104033 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2093. Min Act: -0.0004

Data Index: 1358980 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2146. Min Act: -0.0003

Data Index: 621967 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2123. Min Act: -0.0003

Data Index: 526142 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.1938. Min Act: -0.0003

Data Index: 1262048 (C4 (Web Text))

Max Activating Token Index: 731