Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 77 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0041. Min Act: -0.0006

Data Index: 18137 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0040. Min Act: -0.0006

Data Index: 190146 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0006

Data Index: 1261549 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0006

Data Index: 868412 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0039. Min Act: -0.0006

Data Index: 603486 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0006

Data Index: 529424 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0037. Min Act: -0.0006

Data Index: 672017 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0006

Data Index: 1318381 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0037. Min Act: -0.0006

Data Index: 183307 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1084700 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0036. Min Act: -0.0006

Data Index: 65967 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1353357 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0035. Min Act: -0.0006

Data Index: 547236 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0036. Min Act: -0.0005

Data Index: 963501 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0033. Min Act: -0.0006

Data Index: 920262 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0035. Min Act: -0.0006

Data Index: 426896 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0034. Min Act: -0.0006

Data Index: 79046 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0035. Min Act: -0.0006

Data Index: 437166 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1386238 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1623335 (Python Code)

Max Activating Token Index: 750