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

Dataset: The Pile

Neuron 3693 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: 1.2860. Min Range: -1.2860

Max Act: 1.2860. Min Act: -0.0000

Data Index: 222966 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.0250. Min Act: -0.0000

Data Index: 109354 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1249696 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1450331 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1479919 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1161853 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8311. Min Act: -0.0000

Data Index: 605876 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8454. Min Act: -0.0000

Data Index: 226005 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1916331 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1173623 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8152. Min Act: -0.0000

Data Index: 123261 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1499177 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8857. Min Act: -0.0000

Data Index: 251296 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1427500 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8731. Min Act: -0.0000

Data Index: 252171 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.7408. Min Act: -0.0000

Data Index: 832042 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8693. Min Act: -0.0001

Data Index: 1602246 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.7506. Min Act: -0.0000

Data Index: 284982 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5596. Min Act: -0.0000

Data Index: 215832 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8305. Min Act: -0.0000

Data Index: 680232 (The Pile)

Max Activating Token Index: 995