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

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

Neuron 3900 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: 0.6353. Min Range: -0.6353

Max Act: 0.6353. Min Act: -0.0001

Data Index: 571679 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5897. Min Act: -0.0002

Data Index: 793884 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5409. Min Act: -0.0002

Data Index: 613652 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5187. Min Act: -0.0001

Data Index: 247061 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5511. Min Act: -0.0002

Data Index: 1001289 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5376. Min Act: -0.0001

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5142. Min Act: -0.0002

Data Index: 732046 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4836. Min Act: -0.0002

Data Index: 452162 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5288. Min Act: -0.0001

Data Index: 30583 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4939. Min Act: -0.0001

Data Index: 218693 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4423. Min Act: -0.0001

Data Index: 981156 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5007. Min Act: -0.0002

Data Index: 1134600 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4820. Min Act: -0.0002

Data Index: 1320857 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5196. Min Act: -0.0002

Data Index: 1337226 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4876. Min Act: -0.0002

Data Index: 1297578 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4892. Min Act: -0.0001

Data Index: 147323 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5077. Min Act: -0.0001

Data Index: 872778 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4918. Min Act: -0.0001

Data Index: 1098123 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4435. Min Act: -0.0001

Data Index: 274898 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4842. Min Act: -0.0002

Data Index: 256166 (C4 (Web Text))

Max Activating Token Index: 18