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

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

Neuron 705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1523299 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1378266 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1437624 (Python Code)

Max Activating Token Index: 537

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1479618 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1484518 (Python Code)

Max Activating Token Index: 521

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1508032 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0973. Min Act: -0.0000

Data Index: 372959 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1560148 (Python Code)

Max Activating Token Index: 327

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1593812 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1403519 (Python Code)

Max Activating Token Index: 769

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1582671 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1617564 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0994. Min Act: -0.0000

Data Index: 18316 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1591535 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1636058 (Python Code)

Max Activating Token Index: 594

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1439875 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1440466 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1433729 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1407000 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1570999 (Python Code)

Max Activating Token Index: 494