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

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

Neuron 202 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: 0.3440. Min Range: -0.3440

Max Act: 0.3440. Min Act: -0.0000

Data Index: 892512 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1252965 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3030. Min Act: -0.0000

Data Index: 292134 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2918. Min Act: -0.0001

Data Index: 849581 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2910. Min Act: -0.0001

Data Index: 946127 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2497. Min Act: -0.0000

Data Index: 811996 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1241406 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2916. Min Act: -0.0000

Data Index: 62240 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1346621 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1316229 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1233290 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1214388 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1237004 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1826. Min Act: -0.0000

Data Index: 729100 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1700. Min Act: -0.0001

Data Index: 413662 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1649. Min Act: -0.0000

Data Index: 687852 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1843. Min Act: -0.0001

Data Index: 810007 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1008961 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1665. Min Act: -0.0000

Data Index: 628855 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.1466. Min Act: -0.0001

Data Index: 749742 (C4 (Web Text))

Max Activating Token Index: 697