Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0001

Data Index: 645474 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1288353 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1057020 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1754. Min Act: -0.0001

Data Index: 718857 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1710. Min Act: -0.0001

Data Index: 887569 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1523. Min Act: -0.0001

Data Index: 540887 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1214178 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1354908 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1201405 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1405. Min Act: -0.0001

Data Index: 445001 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1341. Min Act: -0.0001

Data Index: 640233 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1423. Min Act: -0.0001

Data Index: 109368 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1247. Min Act: -0.0001

Data Index: 758943 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1244. Min Act: -0.0001

Data Index: 367513 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1322. Min Act: -0.0001

Data Index: 262279 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1321. Min Act: -0.0001

Data Index: 248058 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1031856 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1308. Min Act: -0.0001

Data Index: 153410 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1199. Min Act: -0.0001

Data Index: 606590 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1196. Min Act: -0.0001

Data Index: 964352 (C4 (Web Text))

Max Activating Token Index: 744