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

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

Neuron 3617 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4309. Min Act: -0.0000

Data Index: 153954 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1185161 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4394. Min Act: -0.0000

Data Index: 146064 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4255. Min Act: -0.0000

Data Index: 680614 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4251. Min Act: -0.0000

Data Index: 564438 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3804. Min Act: -0.0000

Data Index: 910915 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4137. Min Act: -0.0000

Data Index: 28177 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4040. Min Act: -0.0000

Data Index: 44320 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.4141. Min Act: -0.0000

Data Index: 754819 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3703. Min Act: -0.0000

Data Index: 897604 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1197057 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3437. Min Act: -0.0000

Data Index: 491811 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3918. Min Act: -0.0000

Data Index: 283240 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3907. Min Act: -0.0000

Data Index: 288639 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1071942 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3879. Min Act: -0.0000

Data Index: 492351 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3745. Min Act: -0.0000

Data Index: 95864 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3859. Min Act: -0.0000

Data Index: 408212 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3806. Min Act: -0.0000

Data Index: 181257 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.4394. Min Range: -0.4394

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1269820 (C4 (Web Text))

Max Activating Token Index: 528