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

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

Neuron 2688 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0001

Data Index: 545483 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1758. Min Act: -0.0001

Data Index: 856719 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1751. Min Act: -0.0001

Data Index: 206550 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1515. Min Act: -0.0001

Data Index: 250174 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1126468 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1167337 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1497. Min Act: -0.0001

Data Index: 104988 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1214818 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1549. Min Act: -0.0001

Data Index: 516932 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1239909 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1591. Min Act: -0.0001

Data Index: 887548 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1559. Min Act: -0.0001

Data Index: 608939 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1508. Min Act: -0.0001

Data Index: 1305975 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1034146 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1228092 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1522. Min Act: -0.0001

Data Index: 461573 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1364. Min Act: -0.0001

Data Index: 195457 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1504. Min Act: -0.0001

Data Index: 462676 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1452. Min Act: -0.0001

Data Index: 712236 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1438. Min Act: -0.0001

Data Index: 486081 (C4 (Web Text))

Max Activating Token Index: 544