Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5798 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.6198. Min Act: -0.0000

Data Index: 79860 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5273. Min Act: -0.0000

Data Index: 440468 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5267. Min Act: -0.0000

Data Index: 647679 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.5130. Min Act: -0.0000

Data Index: 976812 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4808. Min Act: -0.0000

Data Index: 752904 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4641. Min Act: -0.0000

Data Index: 423808 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4848. Min Act: -0.0000

Data Index: 822109 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4488. Min Act: -0.0000

Data Index: 288312 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4379. Min Act: -0.0000

Data Index: 521509 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4282. Min Act: -0.0000

Data Index: 423999 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4356. Min Act: -0.0000

Data Index: 96179 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4174. Min Act: -0.0000

Data Index: 470203 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1312556 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4141. Min Act: 0.0000

Data Index: 69865 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3619. Min Act: -0.0000

Data Index: 767164 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4046. Min Act: -0.0000

Data Index: 322912 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4043. Min Act: 0.0000

Data Index: 277815 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4167. Min Act: -0.0000

Data Index: 885654 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1258575 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4125. Min Act: -0.0000

Data Index: 652747 (C4 (Web Text))

Max Activating Token Index: 545