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

Dataset: The Pile

Neuron 3515 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: 0.5268. Min Range: -0.5268

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1941678 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1349222 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4595. Min Act: -0.0000

Data Index: 756709 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4509. Min Act: -0.0000

Data Index: 161390 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1484517 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4146. Min Act: -0.0000

Data Index: 528542 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4622. Min Act: -0.0000

Data Index: 521257 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1242609 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4524. Min Act: -0.0000

Data Index: 890943 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4666. Min Act: -0.0000

Data Index: 332215 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4892. Min Act: -0.0000

Data Index: 94807 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1384493 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4629. Min Act: -0.0000

Data Index: 775723 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4364. Min Act: -0.0000

Data Index: 13650 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4384. Min Act: -0.0000

Data Index: 297895 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1827833 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1645930 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1810181 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1549906 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1595666 (The Pile)

Max Activating Token Index: 346