Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 281 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.8342. Min Act: -0.0000

Data Index: 355631 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6373. Min Act: -0.0001

Data Index: 856009 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6424. Min Act: -0.0001

Data Index: 449908 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1064945 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1320503 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5500. Min Act: -0.0000

Data Index: 367610 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5206. Min Act: -0.0001

Data Index: 448835 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4959. Min Act: -0.0001

Data Index: 587661 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5056. Min Act: -0.0000

Data Index: 530897 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4547. Min Act: -0.0000

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4842. Min Act: -0.0000

Data Index: 623567 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4595. Min Act: -0.0001

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4432. Min Act: -0.0000

Data Index: 242852 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1165171 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4818. Min Act: -0.0001

Data Index: 822687 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1031172 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4777. Min Act: -0.0001

Data Index: 421919 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4422. Min Act: -0.0001

Data Index: 359787 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4435. Min Act: -0.0000

Data Index: 176971 (C4 (Web Text))

Max Activating Token Index: 118