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

Dataset: The Pile

Neuron 1526 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: 0.7466. Min Range: -0.7466

Max Act: 0.7372. Min Act: -0.0000

Data Index: 256220 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1981680 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7429. Min Act: -0.0000

Data Index: 529771 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7466. Min Act: -0.0000

Data Index: 883459 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1126127 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1037476 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1307146 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7166. Min Act: -0.0000

Data Index: 171232 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6660. Min Act: -0.0000

Data Index: 551454 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1881628 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7203. Min Act: -0.0000

Data Index: 726658 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1531779 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1390054 (The Pile)

Max Activating Token Index: 384

Text #13

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6716. Min Act: -0.0000

Data Index: 983116 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1879962 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6350. Min Act: -0.0000

Data Index: 999932 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6522. Min Act: -0.0000

Data Index: 456507 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6982. Min Act: -0.0000

Data Index: 275342 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1029404 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1390145 (The Pile)

Max Activating Token Index: 787