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

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

Neuron 5667 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3963. Min Range: -4.3963

Max Act: 4.3963. Min Act: -0.0000

Data Index: 60268 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 4.3963. Min Range: -4.3963

Max Act: 4.3552. Min Act: -0.0000

Data Index: 375582 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.5660. Min Act: -0.0000

Data Index: 1099938 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 4.3963. Min Range: -4.3963

Max Act: 1.9622. Min Act: -0.0000

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.4123. Min Act: -0.0000

Data Index: 90495 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.1746. Min Act: -0.0000

Data Index: 637581 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.0611. Min Act: -0.0000

Data Index: 54462 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.2581. Min Act: -0.0000

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 4.3963. Min Range: -4.3963

Max Act: 1.9864. Min Act: -0.0000

Data Index: 459684 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.1198. Min Act: -0.0000

Data Index: 1061716 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.0279. Min Act: -0.0000

Data Index: 898934 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.2076. Min Act: -0.0000

Data Index: 295997 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 4.3963. Min Range: -4.3963

Max Act: 1.7148. Min Act: -0.0000

Data Index: 1116186 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.1795. Min Act: -0.0000

Data Index: 280324 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1097309 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.0298. Min Act: -0.0000

Data Index: 1152657 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.0539. Min Act: -0.0000

Data Index: 223815 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 4.3963. Min Range: -4.3963

Max Act: 1.9613. Min Act: -0.0000

Data Index: 632057 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 4.3963. Min Range: -4.3963

Max Act: 2.1780. Min Act: -0.0000

Data Index: 258458 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 4.3963. Min Range: -4.3963

Max Act: 1.9591. Min Act: -0.0000

Data Index: 1025269 (C4 (Web Text))

Max Activating Token Index: 284