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

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

Neuron 2455 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: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0000

Data Index: 124349 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1446. Min Act: -0.0000

Data Index: 897271 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1412. Min Act: -0.0001

Data Index: 774047 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1375. Min Act: -0.0000

Data Index: 631409 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1039102 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1364. Min Act: 0.0000

Data Index: 843113 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1330. Min Act: 0.0001

Data Index: 819873 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1307. Min Act: -0.0000

Data Index: 675499 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1264. Min Act: 0.0000

Data Index: 488911 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1339. Min Act: 0.0000

Data Index: 869757 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1287. Min Act: -0.0000

Data Index: 319486 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1195145 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1222. Min Act: 0.0000

Data Index: 98488 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1218. Min Act: -0.0000

Data Index: 613037 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1214. Min Act: -0.0000

Data Index: 179947 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1240. Min Act: -0.0000

Data Index: 711968 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1130956 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1215. Min Act: -0.0000

Data Index: 282555 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1197. Min Act: -0.0000

Data Index: 854671 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1183. Min Act: -0.0000

Data Index: 430627 (C4 (Web Text))

Max Activating Token Index: 103