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

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

Neuron 279 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: 0.2791. Min Range: -0.2791

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1287222 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2730. Min Act: -0.0001

Data Index: 27310 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2712. Min Act: -0.0001

Data Index: 94593 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2617. Min Act: -0.0001

Data Index: 80418 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1291555 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2472. Min Act: -0.0001

Data Index: 902308 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2522. Min Act: -0.0001

Data Index: 923836 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2320. Min Act: -0.0001

Data Index: 891526 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2476. Min Act: -0.0001

Data Index: 850068 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2553. Min Act: -0.0001

Data Index: 104284 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2364. Min Act: -0.0001

Data Index: 1322621 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2198. Min Act: -0.0001

Data Index: 73816 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1030965 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1313595 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2338. Min Act: -0.0001

Data Index: 641900 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2419. Min Act: -0.0001

Data Index: 52025 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2179. Min Act: -0.0001

Data Index: 531402 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1351751 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2399. Min Act: -0.0001

Data Index: 129313 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2389. Min Act: -0.0001

Data Index: 818913 (C4 (Web Text))

Max Activating Token Index: 426