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

Dataset: The Pile

Neuron 3281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1789871 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.8193. Min Act: -0.0000

Data Index: 1513385 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.9552. Min Act: -0.0000

Data Index: 141216 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.7225. Min Act: -0.0000

Data Index: 1997946 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6196. Min Act: -0.0000

Data Index: 60243 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1717336 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.5319. Min Act: -0.0000

Data Index: 1752599 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1453202 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.3780. Min Act: -0.0000

Data Index: 792594 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1296372 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.6204. Min Act: -0.0000

Data Index: 150151 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.3797. Min Act: -0.0000

Data Index: 924717 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1531926 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.4340. Min Act: -0.0000

Data Index: 330434 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1270884 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1272132 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1859480 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1132060 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1136431 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 1.9552. Min Range: -1.9552

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1131938 (The Pile)

Max Activating Token Index: 219