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

Dataset: The Pile

Neuron 3606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5567. Min Act: -0.0000

Data Index: 247348 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4972. Min Act: -0.0000

Data Index: 255599 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4315. Min Act: -0.0000

Data Index: 134375 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1504205 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3773. Min Act: -0.0000

Data Index: 946264 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4560. Min Act: -0.0000

Data Index: 472557 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3823. Min Act: -0.0000

Data Index: 844548 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1810786 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1246684 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1331536 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1891393 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.2899. Min Act: -0.0000

Data Index: 615771 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3634. Min Act: -0.0000

Data Index: 640856 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1484744 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3167. Min Act: -0.0000

Data Index: 124686 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3147. Min Act: -0.0000

Data Index: 284595 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1370028 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1819542 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3339. Min Act: -0.0000

Data Index: 344082 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1862224 (The Pile)

Max Activating Token Index: 78