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

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

Neuron 2415 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0080. Min Range: -1.0080

Max Act: 1.0080. Min Act: -0.0002

Data Index: 97269 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9292. Min Act: -0.0002

Data Index: 146665 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8644. Min Act: -0.0001

Data Index: 320401 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8513. Min Act: -0.0001

Data Index: 552202 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8528. Min Act: -0.0002

Data Index: 1150620 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8734. Min Act: -0.0002

Data Index: 26218 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8662. Min Act: -0.0001

Data Index: 515935 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1047059 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8434. Min Act: -0.0002

Data Index: 84574 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8452. Min Act: -0.0001

Data Index: 938033 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7183. Min Act: -0.0002

Data Index: 968077 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7479. Min Act: -0.0001

Data Index: 208113 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7893. Min Act: -0.0001

Data Index: 1233420 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7394. Min Act: -0.0002

Data Index: 201748 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7536. Min Act: -0.0001

Data Index: 740393 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1127429 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7385. Min Act: -0.0001

Data Index: 783203 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7165. Min Act: -0.0001

Data Index: 836699 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8222. Min Act: -0.0001

Data Index: 264343 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1281189 (C4 (Web Text))

Max Activating Token Index: 580