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

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

Neuron 973 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: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0006

Data Index: 375778 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0586. Min Act: -0.0006

Data Index: 239422 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0601. Min Act: -0.0006

Data Index: 456509 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1345061 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0566. Min Act: -0.0006

Data Index: 346255 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0572. Min Act: -0.0006

Data Index: 143900 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0557. Min Act: -0.0006

Data Index: 412096 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0559. Min Act: -0.0006

Data Index: 784177 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0513. Min Act: -0.0006

Data Index: 1135381 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0533. Min Act: -0.0006

Data Index: 946114 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0513. Min Act: -0.0006

Data Index: 646184 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0532. Min Act: -0.0006

Data Index: 628379 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0526. Min Act: -0.0006

Data Index: 656274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0531. Min Act: -0.0006

Data Index: 587905 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0511. Min Act: -0.0006

Data Index: 384900 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0490. Min Act: -0.0006

Data Index: 129679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0507. Min Act: -0.0006

Data Index: 727286 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0527. Min Act: -0.0006

Data Index: 1177634 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0540. Min Act: -0.0006

Data Index: 115278 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0506. Min Act: -0.0006

Data Index: 75094 (C4 (Web Text))

Max Activating Token Index: 594