Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 815 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0005

Data Index: 233750 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0433. Min Act: -0.0005

Data Index: 448784 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0430. Min Act: -0.0005

Data Index: 575679 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0425. Min Act: -0.0005

Data Index: 303677 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0431. Min Act: -0.0005

Data Index: 116842 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0406. Min Act: -0.0005

Data Index: 705 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0294. Min Act: -0.0005

Data Index: 1233501 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0282. Min Act: -0.0005

Data Index: 983481 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0312. Min Act: -0.0005

Data Index: 350497 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0302. Min Act: -0.0005

Data Index: 1125577 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0319. Min Act: -0.0005

Data Index: 272056 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0282. Min Act: -0.0005

Data Index: 588491 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0268. Min Act: -0.0005

Data Index: 347697 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0288. Min Act: -0.0005

Data Index: 1247587 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0262. Min Act: -0.0005

Data Index: 278209 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0267. Min Act: -0.0005

Data Index: 575710 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0269. Min Act: -0.0005

Data Index: 463964 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0267. Min Act: -0.0005

Data Index: 618550 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0263. Min Act: -0.0005

Data Index: 876233 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0270. Min Act: -0.0005

Data Index: 211208 (C4 (Web Text))

Max Activating Token Index: 902