Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2151 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3248. Min Act: -0.0000

Data Index: 402117 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1612502 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1305429 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3286. Min Act: -0.0000

Data Index: 810559 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3196. Min Act: -0.0000

Data Index: 285972 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1459982 (Python Code)

Max Activating Token Index: 582

Text #6

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1584956 (Python Code)

Max Activating Token Index: 341

Text #7

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2760. Min Act: -0.0000

Data Index: 587044 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1588257 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1594992 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1619313 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1163650 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1450298 (Python Code)

Max Activating Token Index: 66

Text #13

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1346623 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1655986 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2618. Min Act: -0.0000

Data Index: 376047 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2690. Min Act: -0.0000

Data Index: 212622 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2661. Min Act: -0.0001

Data Index: 1636225 (Python Code)

Max Activating Token Index: 254

Text #18

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1427882 (Python Code)

Max Activating Token Index: 889

Text #19

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2700. Min Act: -0.0000

Data Index: 944823 (C4 (Web Text))

Max Activating Token Index: 424