Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7286. Min Act: -0.0003

Data Index: 324868 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7145. Min Act: -0.0003

Data Index: 228377 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7154. Min Act: -0.0003

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7359. Min Act: -0.0003

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7351. Min Act: -0.0003

Data Index: 237391 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7075. Min Act: -0.0003

Data Index: 287974 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6826. Min Act: -0.0003

Data Index: 382590 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6557. Min Act: -0.0003

Data Index: 1082614 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7095. Min Act: -0.0003

Data Index: 1338386 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6860. Min Act: -0.0003

Data Index: 1082032 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7405. Min Act: -0.0003

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6531. Min Act: -0.0003

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.7055. Min Act: -0.0003

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6266. Min Act: -0.0003

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6745. Min Act: -0.0003

Data Index: 723538 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6775. Min Act: -0.0003

Data Index: 551587 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6718. Min Act: -0.0003

Data Index: 701243 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6652. Min Act: -0.0003

Data Index: 1026602 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6238. Min Act: -0.0003

Data Index: 4574 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.7405. Min Range: -0.7405

Max Act: 0.6821. Min Act: -0.0003

Data Index: 584675 (C4 (Web Text))

Max Activating Token Index: 361