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

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

Neuron 1013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0006

Data Index: 561602 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0364. Min Act: -0.0006

Data Index: 375333 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0374. Min Act: -0.0006

Data Index: 977649 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0389. Min Act: -0.0006

Data Index: 1152345 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1221537 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0375. Min Act: -0.0006

Data Index: 1168258 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1143589 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0361. Min Act: -0.0006

Data Index: 721564 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1098803 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0299. Min Act: -0.0006

Data Index: 161785 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0312. Min Act: -0.0005

Data Index: 721905 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0319. Min Act: -0.0006

Data Index: 660333 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1386399 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1400837 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0301. Min Act: -0.0006

Data Index: 339199 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0282. Min Act: -0.0006

Data Index: 367570 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0299. Min Act: -0.0006

Data Index: 581717 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0297. Min Act: -0.0006

Data Index: 963847 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0280. Min Act: -0.0006

Data Index: 49954 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0296. Min Act: -0.0006

Data Index: 604437 (C4 (Web Text))

Max Activating Token Index: 373