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

Dataset: The Pile

Neuron 3402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7965. Min Act: -0.0000

Data Index: 691071 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7259. Min Act: -0.0000

Data Index: 816256 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6919. Min Act: -0.0000

Data Index: 590550 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1564308 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1469964 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6386. Min Act: -0.0000

Data Index: 175801 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1079890 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6301. Min Act: -0.0000

Data Index: 250988 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1114910 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1449400 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1391217 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1206219 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1316135 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6421. Min Act: -0.0000

Data Index: 310659 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6164. Min Act: -0.0000

Data Index: 873900 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1039720 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6280. Min Act: -0.0000

Data Index: 421580 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1624724 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1198407 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6477. Min Act: -0.0000

Data Index: 343290 (The Pile)

Max Activating Token Index: 544