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

Dataset: The Pile

Neuron 4923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3620. Min Act: -0.0000

Data Index: 215117 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3257. Min Act: -0.0000

Data Index: 295995 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3309. Min Act: -0.0000

Data Index: 491933 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3320. Min Act: -0.0000

Data Index: 162422 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3180. Min Act: -0.0000

Data Index: 393531 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3040. Min Act: -0.0000

Data Index: 249028 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1880291 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2869. Min Act: -0.0000

Data Index: 989264 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1983565 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1282130 (The Pile)

Max Activating Token Index: 266

Text #10

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2311. Min Act: -0.0000

Data Index: 7368 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2457. Min Act: -0.0000

Data Index: 281735 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2449. Min Act: -0.0000

Data Index: 665146 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1958967 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2436. Min Act: -0.0000

Data Index: 996914 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2380. Min Act: -0.0000

Data Index: 726289 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1792466 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1746832 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1927377 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1857008 (The Pile)

Max Activating Token Index: 360