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

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

Neuron 4840 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.7390. Min Act: -0.0000

Data Index: 250386 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.7114. Min Act: -0.0000

Data Index: 379927 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6921. Min Act: -0.0000

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6442. Min Act: -0.0000

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1004801 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1037701 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6522. Min Act: -0.0000

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6302. Min Act: -0.0000

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6226. Min Act: -0.0000

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1298262 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6563. Min Act: -0.0000

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6211. Min Act: -0.0000

Data Index: 425341 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6020. Min Act: -0.0000

Data Index: 89031 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1219727 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5554. Min Act: -0.0000

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5552. Min Act: -0.0000

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1064515 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.7390. Min Range: -0.7390

Max Act: 0.5802. Min Act: -0.0000

Data Index: 478271 (C4 (Web Text))

Max Activating Token Index: 686