Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.5539. Min Act: -0.0000

Data Index: 91346 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.5273. Min Act: -0.0000

Data Index: 295252 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4835. Min Act: -0.0000

Data Index: 551311 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4849. Min Act: -0.0000

Data Index: 532809 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4689. Min Act: -0.0000

Data Index: 413193 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1085913 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4558. Min Act: -0.0001

Data Index: 623980 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1331643 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4633. Min Act: -0.0000

Data Index: 45548 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1203184 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1079868 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1262566 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4587. Min Act: -0.0000

Data Index: 588143 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4498. Min Act: -0.0000

Data Index: 981338 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1031749 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4319. Min Act: -0.0001

Data Index: 954614 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4289. Min Act: -0.0000

Data Index: 558279 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1136130 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1187561 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.5539. Min Range: -0.5539

Max Act: 0.4214. Min Act: -0.0000

Data Index: 550379 (C4 (Web Text))

Max Activating Token Index: 771