Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 477 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0001

Data Index: 775654 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1050314 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0350. Min Act: -0.0001

Data Index: 296463 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1257501 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0343. Min Act: -0.0002

Data Index: 307886 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0333. Min Act: -0.0002

Data Index: 8419 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0328. Min Act: -0.0002

Data Index: 98288 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0326. Min Act: -0.0002

Data Index: 116548 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0330. Min Act: -0.0002

Data Index: 414398 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1343821 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0314. Min Act: -0.0002

Data Index: 474000 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0003

Data Index: 947569 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0312. Min Act: -0.0002

Data Index: 696023 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1125746 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1296457 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0002

Data Index: 43711 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1018932 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0304. Min Act: -0.0002

Data Index: 755249 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1180715 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0306. Min Act: -0.0002

Data Index: 954890 (C4 (Web Text))

Max Activating Token Index: 779