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

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

Neuron 1414 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.2734. Min Act: -0.0001

Data Index: 533339 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.1159. Min Act: -0.0001

Data Index: 358618 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.0215. Min Act: -0.0001

Data Index: 1345973 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.0101. Min Act: -0.0001

Data Index: 976782 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.0016. Min Act: -0.0001

Data Index: 94052 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1337082 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9397. Min Act: -0.0001

Data Index: 1589322 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.0224. Min Act: -0.0001

Data Index: 538954 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9586. Min Act: -0.0001

Data Index: 1005230 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9505. Min Act: -0.0001

Data Index: 1170485 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9410. Min Act: -0.0001

Data Index: 924422 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9594. Min Act: -0.0001

Data Index: 1359433 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1106431 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9492. Min Act: -0.0001

Data Index: 748945 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9167. Min Act: -0.0001

Data Index: 636657 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.8927. Min Act: -0.0001

Data Index: 1078298 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9670. Min Act: -0.0001

Data Index: 809998 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9113. Min Act: -0.0001

Data Index: 442209 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9686. Min Act: -0.0001

Data Index: 271022 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.8585. Min Act: -0.0001

Data Index: 1006611 (C4 (Web Text))

Max Activating Token Index: 797