Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 592 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0006

Data Index: 598261 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0351. Min Act: -0.0006

Data Index: 795933 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0356. Min Act: -0.0006

Data Index: 741704 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0353. Min Act: -0.0006

Data Index: 448267 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1334486 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0341. Min Act: -0.0006

Data Index: 174569 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0341. Min Act: -0.0006

Data Index: 641660 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1086244 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0338. Min Act: -0.0006

Data Index: 929702 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0006

Data Index: 86825 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0338. Min Act: -0.0006

Data Index: 151773 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1178174 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1102569 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0330. Min Act: -0.0006

Data Index: 618346 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1079841 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1341203 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1018683 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0318. Min Act: -0.0006

Data Index: 823419 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0321. Min Act: -0.0006

Data Index: 238757 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1123754 (C4 (Web Text))

Max Activating Token Index: 775