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

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

Neuron 3253 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: 1.4349. Min Range: -1.4349

Max Act: 1.4349. Min Act: 0.0000

Data Index: 224744 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.3898. Min Act: -0.0000

Data Index: 531734 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.2952. Min Act: -0.0000

Data Index: 315026 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.3396. Min Act: -0.0000

Data Index: 12252 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.2518. Min Act: -0.0000

Data Index: 835431 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.2307. Min Act: 0.0000

Data Index: 674495 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1400. Min Act: -0.0000

Data Index: 431770 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1257. Min Act: -0.0000

Data Index: 555463 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1236043 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1939. Min Act: -0.0000

Data Index: 675412 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.2343. Min Act: -0.0000

Data Index: 7258 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1332589 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1935. Min Act: -0.0000

Data Index: 609535 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1064714 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.1367. Min Act: 0.0000

Data Index: 977479 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.0885. Min Act: -0.0000

Data Index: 566399 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.0895. Min Act: -0.0000

Data Index: 985468 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.0860. Min Act: -0.0000

Data Index: 420647 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 1.4349. Min Range: -1.4349

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1273384 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 1.4349. Min Range: -1.4349

Max Act: 0.9990. Min Act: -0.0000

Data Index: 241610 (C4 (Web Text))

Max Activating Token Index: 267