Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5442 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.6465. Min Act: -0.0000

Data Index: 723560 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5741. Min Act: -0.0000

Data Index: 919264 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1038250 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5449. Min Act: -0.0000

Data Index: 576060 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5594. Min Act: -0.0000

Data Index: 568349 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1292054 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5060. Min Act: -0.0000

Data Index: 215301 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.5191. Min Act: -0.0000

Data Index: 177912 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4707. Min Act: -0.0000

Data Index: 535332 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4964. Min Act: -0.0000

Data Index: 243559 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1349395 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4592. Min Act: -0.0000

Data Index: 417455 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4308. Min Act: -0.0000

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4695. Min Act: -0.0000

Data Index: 864906 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1152996 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1093384 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4526. Min Act: -0.0000

Data Index: 771767 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4449. Min Act: -0.0000

Data Index: 393807 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1236202 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.6465. Min Range: -0.6465

Max Act: 0.4288. Min Act: -0.0000

Data Index: 194193 (C4 (Web Text))

Max Activating Token Index: 709