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

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

Neuron 2420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1385714 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1183670 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1497478 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1386583 (Python Code)

Max Activating Token Index: 844

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1407244 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0603. Min Act: -0.0000

Data Index: 57178 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0544. Min Act: -0.0000

Data Index: 726445 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0502. Min Act: -0.0000

Data Index: 832588 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0514. Min Act: -0.0000

Data Index: 565583 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0582. Min Act: -0.0000

Data Index: 405376 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0471. Min Act: -0.0001

Data Index: 125498 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0447. Min Act: -0.0000

Data Index: 820821 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0450. Min Act: -0.0000

Data Index: 320530 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1575141 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1345001 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1105264 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0452. Min Act: -0.0000

Data Index: 304974 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0454. Min Act: -0.0000

Data Index: 683008 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1398514 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0435. Min Act: -0.0000

Data Index: 152673 (C4 (Web Text))

Max Activating Token Index: 513