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

Dataset: The Pile

Neuron 3278 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: 0.9894. Min Range: -0.9894

Max Act: 0.9894. Min Act: -0.0000

Data Index: 716448 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1407484 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1203768 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9343. Min Act: -0.0000

Data Index: 6174 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9313. Min Act: -0.0000

Data Index: 651065 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.9247. Min Act: -0.0000

Data Index: 814163 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8605. Min Act: -0.0000

Data Index: 625013 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8768. Min Act: -0.0000

Data Index: 238737 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1060944 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8335. Min Act: -0.0000

Data Index: 394341 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1548955 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8254. Min Act: -0.0000

Data Index: 980657 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1965761 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7957. Min Act: -0.0000

Data Index: 460436 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8384. Min Act: -0.0000

Data Index: 395734 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1703122 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1560559 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1529535 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1699662 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1677044 (The Pile)

Max Activating Token Index: 856