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

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

Neuron 3144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.8092. Min Act: -0.0000

Data Index: 471779 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.8039. Min Act: -0.0000

Data Index: 860144 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.7674. Min Act: -0.0000

Data Index: 840720 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.7517. Min Act: -0.0000

Data Index: 348185 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6817. Min Act: -0.0000

Data Index: 944771 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6971. Min Act: -0.0000

Data Index: 204349 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.7241. Min Act: -0.0000

Data Index: 973957 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6712. Min Act: -0.0000

Data Index: 428117 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6904. Min Act: -0.0000

Data Index: 58455 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1194349 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6378. Min Act: -0.0000

Data Index: 88570 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6276. Min Act: -0.0000

Data Index: 934811 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6295. Min Act: -0.0000

Data Index: 866151 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6349. Min Act: -0.0000

Data Index: 101152 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6328. Min Act: -0.0000

Data Index: 341963 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1204622 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6313. Min Act: -0.0000

Data Index: 575865 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6501. Min Act: -0.0000

Data Index: 802011 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1028488 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.8092. Min Range: -0.8092

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1265800 (C4 (Web Text))

Max Activating Token Index: 449