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

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

Neuron 5644 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.3732. Min Act: -0.0000

Data Index: 961120 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1640475 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.2548. Min Act: -0.0000

Data Index: 336308 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.2334. Min Act: -0.0000

Data Index: 538791 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.1545. Min Act: -0.0000

Data Index: 526873 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1145911 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.0328. Min Act: -0.0000

Data Index: 440069 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1236317 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.0636. Min Act: -0.0000

Data Index: 22279 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 1.3732. Min Range: -1.3732

Max Act: 1.0171. Min Act: -0.0000

Data Index: 726137 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9023. Min Act: -0.0000

Data Index: 84400 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1327799 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9544. Min Act: -0.0000

Data Index: 570663 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9842. Min Act: -0.0000

Data Index: 810432 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9238. Min Act: -0.0000

Data Index: 194505 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9073. Min Act: -0.0000

Data Index: 207406 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9351. Min Act: -0.0000

Data Index: 246948 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.8852. Min Act: -0.0000

Data Index: 122583 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1287955 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.3732. Min Range: -1.3732

Max Act: 0.9012. Min Act: -0.0000

Data Index: 145564 (C4 (Web Text))

Max Activating Token Index: 822