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

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

Neuron 3627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2697. Min Act: -0.0000

Data Index: 9194 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2651. Min Act: -0.0001

Data Index: 846595 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2823. Min Act: -0.0001

Data Index: 753304 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1177756 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2506. Min Act: -0.0001

Data Index: 594368 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2519. Min Act: -0.0001

Data Index: 913792 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2675. Min Act: -0.0001

Data Index: 1039473 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2490. Min Act: -0.0001

Data Index: 573557 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2412. Min Act: -0.0000

Data Index: 243625 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2455. Min Act: -0.0001

Data Index: 91695 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1237649 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2363. Min Act: -0.0000

Data Index: 987517 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2390. Min Act: -0.0001

Data Index: 10159 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2458. Min Act: -0.0001

Data Index: 63883 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2303. Min Act: -0.0001

Data Index: 490876 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2503. Min Act: -0.0001

Data Index: 754986 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2254. Min Act: -0.0001

Data Index: 1221932 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1168058 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2169. Min Act: -0.0000

Data Index: 106637 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2230. Min Act: -0.0000

Data Index: 343938 (C4 (Web Text))

Max Activating Token Index: 549