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

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

Neuron 4286 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1165036 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2815. Min Act: -0.0001

Data Index: 24033 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2730. Min Act: -0.0001

Data Index: 485842 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1340947 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2570. Min Act: -0.0001

Data Index: 615953 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2455. Min Act: -0.0001

Data Index: 293601 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2500. Min Act: -0.0001

Data Index: 94779 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2420. Min Act: -0.0001

Data Index: 412431 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2447. Min Act: -0.0001

Data Index: 995519 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2418. Min Act: -0.0001

Data Index: 34544 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2418. Min Act: -0.0001

Data Index: 829115 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2336. Min Act: -0.0001

Data Index: 442784 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2346. Min Act: -0.0001

Data Index: 228727 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1036691 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2339. Min Act: -0.0001

Data Index: 686535 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1060598 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1171441 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2314. Min Act: -0.0001

Data Index: 670038 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1128725 (C4 (Web Text))

Max Activating Token Index: 403