Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4813 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.2647. Min Act: -0.0000

Data Index: 96567 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9113. Min Act: -0.0000

Data Index: 820121 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7792. Min Act: -0.0000

Data Index: 369220 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.8207. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7779. Min Act: -0.0000

Data Index: 903215 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1195228 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7858. Min Act: -0.0000

Data Index: 651084 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.8103. Min Act: -0.0000

Data Index: 534211 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.6935. Min Act: -0.0000

Data Index: 590178 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7272. Min Act: -0.0000

Data Index: 956559 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7318. Min Act: -0.0000

Data Index: 560931 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7369. Min Act: -0.0000

Data Index: 954894 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7037. Min Act: -0.0000

Data Index: 376710 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1119517 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.7140. Min Act: -0.0000

Data Index: 107272 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.6661. Min Act: -0.0000

Data Index: 444195 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.6613. Min Act: -0.0000

Data Index: 399467 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1129131 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.6850. Min Act: -0.0000

Data Index: 184499 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1190372 (C4 (Web Text))

Max Activating Token Index: 723