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

Dataset: The Pile

Neuron 320 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: 0.3253. Min Range: -0.3253

Max Act: 0.3253. Min Act: -0.0000

Data Index: 555280 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2750. Min Act: -0.0000

Data Index: 505997 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1848825 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2622. Min Act: -0.0000

Data Index: 534374 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2459. Min Act: -0.0000

Data Index: 118240 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2253. Min Act: -0.0001

Data Index: 644000 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1992. Min Act: -0.0000

Data Index: 459780 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2324. Min Act: -0.0000

Data Index: 91070 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2016. Min Act: -0.0000

Data Index: 404712 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2184. Min Act: -0.0000

Data Index: 736179 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1911322 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2051. Min Act: -0.0000

Data Index: 89491 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2162. Min Act: -0.0000

Data Index: 801843 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1721232 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1952. Min Act: -0.0000

Data Index: 761544 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1914. Min Act: -0.0000

Data Index: 514603 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2050. Min Act: -0.0000

Data Index: 433494 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2148. Min Act: -0.0000

Data Index: 544066 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1953. Min Act: -0.0000

Data Index: 878367 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1987. Min Act: -0.0000

Data Index: 111505 (The Pile)

Max Activating Token Index: 352