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

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

Neuron 4001 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: 0.3458. Min Range: -0.3458

Max Act: 0.3358. Min Act: -0.0000

Data Index: 409297 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3458. Min Act: -0.0000

Data Index: 486851 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2815. Min Act: -0.0001

Data Index: 905022 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2661. Min Act: -0.0001

Data Index: 400473 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2527. Min Act: -0.0000

Data Index: 723072 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2510. Min Act: -0.0000

Data Index: 717087 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1315403 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2255. Min Act: -0.0001

Data Index: 854208 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2259. Min Act: -0.0000

Data Index: 947391 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2375. Min Act: -0.0000

Data Index: 282688 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2343. Min Act: -0.0000

Data Index: 498183 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2270. Min Act: -0.0000

Data Index: 921000 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2284. Min Act: -0.0000

Data Index: 112322 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2171. Min Act: -0.0000

Data Index: 426779 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2154. Min Act: -0.0001

Data Index: 615206 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1084937 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2063. Min Act: -0.0000

Data Index: 238884 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1308111 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2154. Min Act: -0.0001

Data Index: 544502 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2061. Min Act: -0.0000

Data Index: 994428 (C4 (Web Text))

Max Activating Token Index: 424