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

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

Neuron 3544 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: 0.7038. Min Range: -0.7038

Max Act: 0.7038. Min Act: -0.0002

Data Index: 519633 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6927. Min Act: -0.0001

Data Index: 201320 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5717. Min Act: -0.0001

Data Index: 590436 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6044. Min Act: -0.0002

Data Index: 581406 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5763. Min Act: -0.0001

Data Index: 148537 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4865. Min Act: -0.0001

Data Index: 648577 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5472. Min Act: -0.0001

Data Index: 939361 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5303. Min Act: -0.0001

Data Index: 1277822 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5233. Min Act: -0.0001

Data Index: 899307 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5179. Min Act: -0.0001

Data Index: 1299771 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5373. Min Act: -0.0002

Data Index: 607678 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5095. Min Act: -0.0001

Data Index: 174507 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4966. Min Act: -0.0001

Data Index: 1306045 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5224. Min Act: -0.0001

Data Index: 668355 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4799. Min Act: -0.0001

Data Index: 1255279 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1296853 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4830. Min Act: -0.0002

Data Index: 694889 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4898. Min Act: -0.0001

Data Index: 598524 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4913. Min Act: -0.0001

Data Index: 1132907 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4861. Min Act: -0.0001

Data Index: 262622 (C4 (Web Text))

Max Activating Token Index: 352