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

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

Neuron 3621 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: 0.1583. Min Range: -0.1583

Max Act: 0.1583. Min Act: -0.0000

Data Index: 827142 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1562. Min Act: -0.0000

Data Index: 446351 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1553. Min Act: -0.0000

Data Index: 177291 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1470. Min Act: -0.0000

Data Index: 51920 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1076605 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1479. Min Act: -0.0000

Data Index: 139581 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1407. Min Act: -0.0000

Data Index: 839521 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1447264 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1174013 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1357419 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1311. Min Act: -0.0000

Data Index: 382488 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1215. Min Act: -0.0001

Data Index: 862759 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1644436 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1224. Min Act: -0.0000

Data Index: 785902 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1361955 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1182. Min Act: -0.0001

Data Index: 172315 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1291. Min Act: -0.0000

Data Index: 985304 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1193. Min Act: -0.0000

Data Index: 255115 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1255. Min Act: -0.0000

Data Index: 236710 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.1583. Min Range: -0.1583

Max Act: 0.1177. Min Act: -0.0000

Data Index: 516408 (C4 (Web Text))

Max Activating Token Index: 975