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

Dataset: The Pile

Neuron 2296 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1894819 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5159. Min Act: -0.0000

Data Index: 828939 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1568510 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4671. Min Act: -0.0000

Data Index: 390061 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1046811 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1273435 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4557. Min Act: -0.0000

Data Index: 967606 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4370. Min Act: -0.0000

Data Index: 615929 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4359. Min Act: -0.0000

Data Index: 611335 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4368. Min Act: -0.0000

Data Index: 252021 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4630. Min Act: -0.0000

Data Index: 960300 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4142. Min Act: -0.0000

Data Index: 466693 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1162701 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4354. Min Act: 0.0000

Data Index: 712058 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4321. Min Act: 0.0000

Data Index: 137344 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4236. Min Act: -0.0000

Data Index: 158523 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1707747 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4075. Min Act: -0.0000

Data Index: 570921 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4336. Min Act: -0.0000

Data Index: 213223 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1287964 (The Pile)

Max Activating Token Index: 421