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

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

Neuron 3987 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3658. Min Act: -0.0001

Data Index: 90554 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.2006. Min Act: -0.0001

Data Index: 331572 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4652. Min Act: -0.0001

Data Index: 854404 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3181. Min Act: -0.0001

Data Index: 401430 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.1484. Min Act: -0.0001

Data Index: 13173 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3682. Min Act: -0.0001

Data Index: 1077816 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3670. Min Act: -0.0001

Data Index: 861321 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.5002. Min Act: -0.0001

Data Index: 1112340 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.6466. Min Act: -0.0001

Data Index: 940827 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4647. Min Act: -0.0001

Data Index: 39109 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.4914. Min Act: -0.0001

Data Index: 278602 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.0962. Min Act: -0.0001

Data Index: 1094257 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3833. Min Act: -0.0001

Data Index: 76601 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.5244. Min Act: -0.0001

Data Index: 1186000 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3525. Min Act: -0.0001

Data Index: 1320291 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.5055. Min Act: -0.0001

Data Index: 221346 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3698. Min Act: -0.0001

Data Index: 460074 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.0677. Min Act: -0.0001

Data Index: 578991 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.3521. Min Act: -0.0001

Data Index: 839134 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.6466. Min Range: -3.6466

Max Act: 3.0460. Min Act: -0.0001

Data Index: 180220 (C4 (Web Text))

Max Activating Token Index: 382