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

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

Neuron 1163 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.4729. Min Act: -0.0000

Data Index: 434152 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 6.4729. Min Range: -6.4729

Max Act: 5.8430. Min Act: -0.0000

Data Index: 187891 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 6.4729. Min Range: -6.4729

Max Act: 5.3286. Min Act: -0.0000

Data Index: 228042 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 6.4729. Min Range: -6.4729

Max Act: 5.8132. Min Act: -0.0000

Data Index: 465330 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 6.4729. Min Range: -6.4729

Max Act: 5.5298. Min Act: -0.0000

Data Index: 95981 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.0279. Min Act: -0.0000

Data Index: 675190 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 6.4729. Min Range: -6.4729

Max Act: 5.0337. Min Act: -0.0000

Data Index: 440383 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.4838. Min Act: -0.0000

Data Index: 850558 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.4166. Min Act: -0.0000

Data Index: 765937 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.7744. Min Act: -0.0000

Data Index: 1165359 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.2161. Min Act: -0.0000

Data Index: 468257 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.8485. Min Act: -0.0000

Data Index: 60929 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.2825. Min Act: -0.0000

Data Index: 501675 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.2127. Min Act: -0.0000

Data Index: 1174735 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.7188. Min Act: -0.0000

Data Index: 900525 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.6954. Min Act: -0.0000

Data Index: 1267746 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.5633. Min Act: -0.0000

Data Index: 574871 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 6.4729. Min Range: -6.4729

Max Act: 5.2462. Min Act: -0.0000

Data Index: 888227 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 6.4729. Min Range: -6.4729

Max Act: 4.8694. Min Act: -0.0000

Data Index: 543434 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 6.4729. Min Range: -6.4729

Max Act: 3.9004. Min Act: -0.0000

Data Index: 148246 (C4 (Web Text))

Max Activating Token Index: 487