Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0598. Min Act: -0.0006

Data Index: 862993 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0006

Data Index: 434247 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0523. Min Act: -0.0006

Data Index: 986649 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0552. Min Act: -0.0006

Data Index: 406608 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0592. Min Act: -0.0006

Data Index: 1071515 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0588. Min Act: -0.0006

Data Index: 956381 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0599. Min Act: -0.0006

Data Index: 411321 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0531. Min Act: -0.0006

Data Index: 503981 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0566. Min Act: -0.0006

Data Index: 140249 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1272163 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0599. Min Act: -0.0006

Data Index: 626645 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0571. Min Act: -0.0006

Data Index: 844264 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1221772 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0549. Min Act: -0.0006

Data Index: 887231 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0524. Min Act: -0.0006

Data Index: 1192798 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0545. Min Act: -0.0006

Data Index: 1047498 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0566. Min Act: -0.0006

Data Index: 1103707 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0562. Min Act: -0.0006

Data Index: 1180304 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0520. Min Act: -0.0006

Data Index: 418551 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0510. Min Act: -0.0006

Data Index: 468965 (C4 (Web Text))

Max Activating Token Index: 461