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

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

Neuron 1454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1095895 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3866. Min Act: -0.0000

Data Index: 323600 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1036825 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4041. Min Act: -0.0000

Data Index: 204581 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3914. Min Act: -0.0001

Data Index: 479126 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3675. Min Act: -0.0000

Data Index: 601719 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1071536 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3534. Min Act: -0.0000

Data Index: 60205 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3354. Min Act: -0.0000

Data Index: 378665 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3365. Min Act: -0.0000

Data Index: 594316 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3350. Min Act: -0.0000

Data Index: 177245 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3551. Min Act: -0.0000

Data Index: 197283 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1318013 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3495. Min Act: -0.0001

Data Index: 224512 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3597. Min Act: -0.0000

Data Index: 911016 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3441. Min Act: -0.0000

Data Index: 439146 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3525. Min Act: -0.0000

Data Index: 160117 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3090. Min Act: -0.0000

Data Index: 206902 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3194. Min Act: -0.0000

Data Index: 152910 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.3287. Min Act: -0.0001

Data Index: 101840 (C4 (Web Text))

Max Activating Token Index: 1013