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

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

Neuron 335 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.6471. Min Act: -0.0000

Data Index: 809774 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.7678. Min Act: -0.0001

Data Index: 1431537 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.4653. Min Act: -0.0000

Data Index: 759945 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.2916. Min Act: -0.0001

Data Index: 1571639 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.1739. Min Act: -0.0001

Data Index: 94175 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.2781. Min Act: -0.0000

Data Index: 593586 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.0953. Min Act: -0.0000

Data Index: 551486 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.0722. Min Act: -0.0001

Data Index: 154048 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.9551. Min Act: -0.0000

Data Index: 103548 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.9356. Min Act: -0.0001

Data Index: 106036 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.9765. Min Act: -0.0000

Data Index: 1195220 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.9628. Min Act: -0.0001

Data Index: 1185410 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.8475. Min Act: -0.0001

Data Index: 1395977 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.9124. Min Act: -0.0001

Data Index: 729869 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.8449. Min Act: -0.0001

Data Index: 384312 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 2.7678. Min Range: -2.7678

Max Act: 2.1082. Min Act: -0.0001

Data Index: 531140 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.8461. Min Act: -0.0000

Data Index: 1512138 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.8171. Min Act: -0.0000

Data Index: 752769 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.8539. Min Act: -0.0000

Data Index: 631594 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 2.7678. Min Range: -2.7678

Max Act: 1.8315. Min Act: -0.0001

Data Index: 718456 (C4 (Web Text))

Max Activating Token Index: 715