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

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

Neuron 4982 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7214. Min Range: -6.7214

Max Act: 6.6481. Min Act: 0.0004

Data Index: 1104870 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 6.7214. Min Range: -6.7214

Max Act: 6.7214. Min Act: -0.0000

Data Index: 1089667 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 6.7214. Min Range: -6.7214

Max Act: 6.0311. Min Act: 0.0000

Data Index: 267122 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 6.7214. Min Range: -6.7214

Max Act: 6.0980. Min Act: -0.0000

Data Index: 176412 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 6.7214. Min Range: -6.7214

Max Act: 6.0950. Min Act: -0.0000

Data Index: 1154655 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.9861. Min Act: -0.0000

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 6.7214. Min Range: -6.7214

Max Act: 6.0601. Min Act: -0.0000

Data Index: 311772 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.8619. Min Act: 0.0001

Data Index: 261034 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.8217. Min Act: -0.0000

Data Index: 830074 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.7979. Min Act: -0.0000

Data Index: 947904 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.4967. Min Act: -0.0000

Data Index: 18062 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.5719. Min Act: 0.0001

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.5668. Min Act: 0.0001

Data Index: 614034 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.0267. Min Act: 0.0004

Data Index: 2620 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 6.7214. Min Range: -6.7214

Max Act: 4.8423. Min Act: -0.0000

Data Index: 593680 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 6.7214. Min Range: -6.7214

Max Act: 4.9930. Min Act: -0.0000

Data Index: 231967 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.1351. Min Act: -0.0000

Data Index: 1195546 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 6.7214. Min Range: -6.7214

Max Act: 5.0360. Min Act: -0.0000

Data Index: 830196 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 6.7214. Min Range: -6.7214

Max Act: 4.5865. Min Act: 0.0001

Data Index: 195599 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 6.7214. Min Range: -6.7214

Max Act: 4.5667. Min Act: -0.0000

Data Index: 1307228 (C4 (Web Text))

Max Activating Token Index: 786