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

Dataset: The Pile

Neuron 4085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1091834 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.6574. Min Act: -0.0000

Data Index: 612633 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1141519 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1114433 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5603. Min Act: -0.0000

Data Index: 306515 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1672054 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5734. Min Act: -0.0000

Data Index: 442115 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5393. Min Act: -0.0000

Data Index: 625080 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5302. Min Act: -0.0000

Data Index: 293453 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5284. Min Act: -0.0000

Data Index: 632047 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5469. Min Act: -0.0000

Data Index: 179561 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1579204 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5245. Min Act: -0.0000

Data Index: 938554 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1525439 (The Pile)

Max Activating Token Index: 934

Text #14

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5288. Min Act: 0.0000

Data Index: 13012 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1769235 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1351185 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1020136 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5042. Min Act: -0.0000

Data Index: 61251 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 0.6574. Min Range: -0.6574

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1099636 (The Pile)

Max Activating Token Index: 414