Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 716 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.9233. Min Act: -0.0001

Data Index: 891236 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.9367. Min Act: -0.0000

Data Index: 738507 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.9027. Min Act: -0.0001

Data Index: 473949 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1047103 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6691. Min Act: -0.0001

Data Index: 1127346 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6210. Min Act: -0.0001

Data Index: 1297296 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6503. Min Act: -0.0001

Data Index: 337521 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.6317. Min Act: -0.0000

Data Index: 379590 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1114444 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5791. Min Act: -0.0000

Data Index: 767995 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5655. Min Act: -0.0001

Data Index: 364167 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5696. Min Act: -0.0001

Data Index: 1178877 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5669. Min Act: -0.0000

Data Index: 130354 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5362. Min Act: -0.0000

Data Index: 94739 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5470. Min Act: -0.0000

Data Index: 62235 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5605. Min Act: -0.0000

Data Index: 14530 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5219. Min Act: -0.0000

Data Index: 419981 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5538. Min Act: -0.0001

Data Index: 348442 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1085453 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.9367. Min Range: -0.9367

Max Act: 0.5267. Min Act: -0.0001

Data Index: 1114333 (C4 (Web Text))

Max Activating Token Index: 421