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

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

Neuron 4750 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: 1.8552. Min Range: -1.8552

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1157060 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.8423. Min Act: -0.0000

Data Index: 809665 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7645. Min Act: -0.0000

Data Index: 412781 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.3930. Min Act: -0.0000

Data Index: 636545 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.3565. Min Act: -0.0000

Data Index: 292347 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1013422 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.2863. Min Act: -0.0000

Data Index: 373278 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1115367 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.1194. Min Act: 0.0000

Data Index: 847896 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.1341. Min Act: -0.0000

Data Index: 325263 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1070047 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.1597. Min Act: -0.0000

Data Index: 577238 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.0553. Min Act: -0.0000

Data Index: 860842 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.8552. Min Range: -1.8552

Max Act: 0.9962. Min Act: -0.0000

Data Index: 85121 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.1712. Min Act: -0.0000

Data Index: 366086 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1147099 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.0559. Min Act: -0.0000

Data Index: 632046 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.8552. Min Range: -1.8552

Max Act: 0.9849. Min Act: -0.0000

Data Index: 167235 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 1.8552. Min Range: -1.8552

Max Act: 0.9744. Min Act: -0.0000

Data Index: 1208831 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.8552. Min Range: -1.8552

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1270164 (C4 (Web Text))

Max Activating Token Index: 94