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

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

Neuron 3358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1007272 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6282. Min Act: -0.0000

Data Index: 361346 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6310. Min Act: -0.0000

Data Index: 382655 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5747. Min Act: -0.0000

Data Index: 386744 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5395. Min Act: -0.0000

Data Index: 489430 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5289. Min Act: -0.0001

Data Index: 213126 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5096. Min Act: -0.0000

Data Index: 473095 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5213. Min Act: -0.0000

Data Index: 836777 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4445. Min Act: -0.0000

Data Index: 33794 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1227057 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4791. Min Act: -0.0000

Data Index: 581064 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1173929 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4243. Min Act: -0.0000

Data Index: 893922 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4638. Min Act: -0.0000

Data Index: 687563 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4401. Min Act: -0.0000

Data Index: 667339 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4207. Min Act: -0.0000

Data Index: 162923 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1343789 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4128. Min Act: -0.0000

Data Index: 213526 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4082. Min Act: -0.0001

Data Index: 26430 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.4103. Min Act: -0.0000

Data Index: 763623 (C4 (Web Text))

Max Activating Token Index: 910