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

Dataset: The Pile

Neuron 2930 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: 0.8520. Min Range: -0.8520

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1045632 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7574. Min Act: -0.0000

Data Index: 867748 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1903446 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1297782 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1685618 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1913838 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1137668 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6994. Min Act: -0.0000

Data Index: 646661 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6685. Min Act: -0.0000

Data Index: 480429 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1419069 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1562663 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1045884 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6795. Min Act: -0.0000

Data Index: 483973 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1962510 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6146. Min Act: -0.0000

Data Index: 947669 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1610578 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6473. Min Act: -0.0000

Data Index: 919300 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1788377 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1588758 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1719402 (The Pile)

Max Activating Token Index: 324