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

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

Neuron 737 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0346. Min Act: -0.0001

Data Index: 1129889 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0293. Min Act: -0.0001

Data Index: 922941 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.0346. Min Range: -1.0346

Max Act: 1.0189. Min Act: -0.0001

Data Index: 705581 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9601. Min Act: -0.0001

Data Index: 989078 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1326188 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.9170. Min Act: -0.0001

Data Index: 1253188 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8992. Min Act: -0.0001

Data Index: 610729 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8732. Min Act: -0.0001

Data Index: 33823 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8659. Min Act: -0.0001

Data Index: 1215078 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8451. Min Act: -0.0001

Data Index: 572991 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8287. Min Act: -0.0001

Data Index: 264338 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8241. Min Act: -0.0001

Data Index: 640227 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8258. Min Act: -0.0001

Data Index: 852909 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7990. Min Act: -0.0001

Data Index: 688311 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8009. Min Act: -0.0001

Data Index: 221397 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7734. Min Act: -0.0001

Data Index: 208024 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8142. Min Act: -0.0001

Data Index: 663327 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7885. Min Act: -0.0001

Data Index: 395394 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.8592. Min Act: -0.0001

Data Index: 1008451 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.0346. Min Range: -1.0346

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1208104 (C4 (Web Text))

Max Activating Token Index: 817