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

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

Neuron 2701 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1357977 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1598. Min Act: -0.0001

Data Index: 484101 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1712. Min Act: -0.0001

Data Index: 1158305 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1543. Min Act: -0.0001

Data Index: 171994 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1342. Min Act: -0.0001

Data Index: 203998 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1440. Min Act: -0.0001

Data Index: 886643 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1536. Min Act: -0.0001

Data Index: 278055 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1420. Min Act: -0.0001

Data Index: 862574 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1174. Min Act: -0.0001

Data Index: 33310 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1543. Min Act: -0.0001

Data Index: 240695 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1257150 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1404. Min Act: -0.0001

Data Index: 598130 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1177. Min Act: -0.0001

Data Index: 33109 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1184. Min Act: -0.0001

Data Index: 266585 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1340. Min Act: -0.0001

Data Index: 443266 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1248. Min Act: -0.0001

Data Index: 62653 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1236. Min Act: -0.0001

Data Index: 186591 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1210. Min Act: -0.0001

Data Index: 396909 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1120. Min Act: -0.0001

Data Index: 397786 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.1986. Min Range: -0.1986

Max Act: 0.1032. Min Act: -0.0001

Data Index: 33339 (C4 (Web Text))

Max Activating Token Index: 265