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

Dataset: The Pile

Neuron 3962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.6253. Min Act: -0.0000

Data Index: 905278 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1327336 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2475. Min Act: -0.0000

Data Index: 276558 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1417522 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1186671 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1548753 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.9758. Min Act: -0.0000

Data Index: 803395 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1263221 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0703. Min Act: 0.0000

Data Index: 1952967 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1516388 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.8495. Min Act: -0.0000

Data Index: 396785 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.8500. Min Act: -0.0000

Data Index: 577686 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1267712 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.9211. Min Act: 0.0000

Data Index: 146599 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.8048. Min Act: 0.0000

Data Index: 1147472 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1170895 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.7275. Min Act: -0.0000

Data Index: 461023 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1059976 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.6960. Min Act: -0.0000

Data Index: 395592 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.7086. Min Act: -0.0000

Data Index: 601451 (The Pile)

Max Activating Token Index: 971