Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1255 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2566. Min Act: -0.0001

Data Index: 113156 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.3425. Min Act: -0.0001

Data Index: 1193974 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0823. Min Act: -0.0001

Data Index: 109745 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1261. Min Act: -0.0001

Data Index: 996493 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1825. Min Act: -0.0001

Data Index: 262950 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.3425. Min Range: -1.3425

Max Act: 0.9278. Min Act: -0.0001

Data Index: 144641 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.3425. Min Range: -1.3425

Max Act: 0.9625. Min Act: -0.0001

Data Index: 1040204 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1533. Min Act: -0.0001

Data Index: 26339 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0907. Min Act: -0.0001

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1395. Min Act: -0.0001

Data Index: 1297870 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0375. Min Act: -0.0001

Data Index: 46392 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1658. Min Act: -0.0001

Data Index: 1207371 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.3425. Min Range: -1.3425

Max Act: 0.9831. Min Act: -0.0001

Data Index: 926585 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0318. Min Act: -0.0001

Data Index: 232335 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0204. Min Act: -0.0001

Data Index: 1279187 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.3425. Min Range: -1.3425

Max Act: 0.9927. Min Act: -0.0001

Data Index: 526749 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.3425. Min Range: -1.3425

Max Act: 0.9290. Min Act: -0.0001

Data Index: 379644 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0139. Min Act: -0.0001

Data Index: 927102 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.3425. Min Range: -1.3425

Max Act: 0.9738. Min Act: -0.0001

Data Index: 1098906 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0053. Min Act: -0.0001

Data Index: 12798 (C4 (Web Text))

Max Activating Token Index: 770