Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2632 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5782. Min Act: -0.0000

Data Index: 365983 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4457. Min Act: -0.0000

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1170948 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4327. Min Act: -0.0000

Data Index: 878957 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1159779 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4435. Min Act: -0.0000

Data Index: 359856 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1305347 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3734. Min Act: -0.0000

Data Index: 983769 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3762. Min Act: -0.0000

Data Index: 382612 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3741. Min Act: -0.0000

Data Index: 146196 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3621. Min Act: -0.0000

Data Index: 814073 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1644410 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1013713 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3678. Min Act: -0.0000

Data Index: 968597 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3327. Min Act: -0.0000

Data Index: 573407 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3303. Min Act: -0.0000

Data Index: 320379 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3433. Min Act: -0.0000

Data Index: 432633 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3359. Min Act: -0.0000

Data Index: 604086 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1301578 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.3291. Min Act: 0.0001

Data Index: 1195848 (C4 (Web Text))

Max Activating Token Index: 617