Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4232 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1266481 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.8225. Min Act: -0.0000

Data Index: 266511 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7620. Min Act: -0.0000

Data Index: 171167 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6937. Min Act: -0.0000

Data Index: 740176 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7469. Min Act: -0.0000

Data Index: 554023 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7035. Min Act: -0.0000

Data Index: 993817 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6762. Min Act: -0.0000

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6873. Min Act: -0.0000

Data Index: 56534 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7248. Min Act: -0.0000

Data Index: 278916 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6734. Min Act: -0.0000

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7354. Min Act: -0.0000

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.7137. Min Act: -0.0000

Data Index: 357396 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6589. Min Act: -0.0000

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6171. Min Act: -0.0000

Data Index: 619942 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6287. Min Act: -0.0000

Data Index: 977805 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1101934 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6168. Min Act: -0.0000

Data Index: 821439 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.6307. Min Act: -0.0000

Data Index: 519707 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.8236. Min Range: -0.8236

Max Act: 0.5878. Min Act: -0.0000

Data Index: 205243 (C4 (Web Text))

Max Activating Token Index: 389