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

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

Neuron 2924 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.5395. Min Act: -0.0000

Data Index: 157098 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1239108 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.5170. Min Act: -0.0000

Data Index: 437655 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.5059. Min Act: -0.0000

Data Index: 713530 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4728. Min Act: -0.0000

Data Index: 957863 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4464. Min Act: -0.0000

Data Index: 476242 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4204. Min Act: -0.0000

Data Index: 903485 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4137. Min Act: -0.0000

Data Index: 72590 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.4118. Min Act: -0.0000

Data Index: 379181 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3782. Min Act: -0.0000

Data Index: 61156 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3893. Min Act: -0.0000

Data Index: 131467 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3988. Min Act: -0.0000

Data Index: 194443 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3953. Min Act: -0.0000

Data Index: 419673 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3702. Min Act: -0.0000

Data Index: 990121 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3659. Min Act: -0.0000

Data Index: 531901 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3371. Min Act: -0.0000

Data Index: 572056 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3305. Min Act: -0.0000

Data Index: 87578 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3028. Min Act: -0.0000

Data Index: 225409 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3365. Min Act: -0.0000

Data Index: 873071 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.5395. Min Range: -0.5395

Max Act: 0.3257. Min Act: -0.0000

Data Index: 805383 (C4 (Web Text))

Max Activating Token Index: 98