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

Dataset: The Pile

Neuron 2188 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6532. Min Act: -0.0000

Data Index: 894640 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1497042 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1497998 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1330045 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6203. Min Act: -0.0000

Data Index: 105657 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.6195. Min Act: -0.0000

Data Index: 809978 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5919. Min Act: -0.0000

Data Index: 183690 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5624. Min Act: -0.0000

Data Index: 95287 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5786. Min Act: -0.0000

Data Index: 224709 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5765. Min Act: -0.0000

Data Index: 650322 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1605628 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5538. Min Act: -0.0000

Data Index: 175751 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1945324 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5572. Min Act: -0.0000

Data Index: 501683 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5712. Min Act: -0.0000

Data Index: 570566 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1152798 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1078951 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5827. Min Act: -0.0000

Data Index: 79645 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1241673 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.6846. Min Range: -0.6846

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1306326 (The Pile)

Max Activating Token Index: 61