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

Dataset: The Pile

Neuron 1070 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: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 925301 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1214193 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5951. Min Act: -0.0000

Data Index: 366246 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6277. Min Act: -0.0000

Data Index: 49670 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5697. Min Act: -0.0000

Data Index: 290092 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5705. Min Act: -0.0000

Data Index: 781321 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5787. Min Act: -0.0000

Data Index: 472190 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1373842 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1875854 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5395. Min Act: -0.0000

Data Index: 422863 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1402707 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.4660. Min Act: -0.0000

Data Index: 74561 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1884364 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1790015 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1547558 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1544726 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1739670 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5364. Min Act: -0.0000

Data Index: 283068 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1058511 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5206. Min Act: -0.0000

Data Index: 189537 (The Pile)

Max Activating Token Index: 130