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

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

Neuron 334 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0002

Data Index: 136971 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0372. Min Act: -0.0002

Data Index: 442535 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0367. Min Act: -0.0002

Data Index: 656401 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0372. Min Act: -0.0002

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0342. Min Act: -0.0002

Data Index: 139953 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0339. Min Act: -0.0002

Data Index: 330006 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0330. Min Act: -0.0002

Data Index: 54175 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0338. Min Act: -0.0002

Data Index: 557049 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1156490 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0330. Min Act: -0.0002

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0330. Min Act: -0.0002

Data Index: 925247 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0333. Min Act: -0.0002

Data Index: 108296 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0335. Min Act: -0.0003

Data Index: 99850 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0330. Min Act: -0.0002

Data Index: 223484 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0329. Min Act: -0.0002

Data Index: 747952 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0329. Min Act: -0.0002

Data Index: 347929 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0327. Min Act: -0.0002

Data Index: 656191 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0328. Min Act: -0.0002

Data Index: 137596 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0327. Min Act: -0.0002

Data Index: 739325 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0315. Min Act: -0.0002

Data Index: 338233 (C4 (Web Text))

Max Activating Token Index: 255