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

Dataset: The Pile

Neuron 1046 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2573. Min Act: 0.0000

Data Index: 543514 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1426738 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1773968 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2458. Min Act: -0.0000

Data Index: 585394 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1743121 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1919945 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2343. Min Act: -0.0000

Data Index: 59815 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1962304 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1290659 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1161969 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2174. Min Act: -0.0000

Data Index: 416731 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2254. Min Act: -0.0000

Data Index: 287456 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1618831 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2106. Min Act: -0.0000

Data Index: 744486 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1096234 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2233. Min Act: -0.0000

Data Index: 702859 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2052. Min Act: -0.0000

Data Index: 616485 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1953979 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2003. Min Act: -0.0000

Data Index: 184385 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1212403 (The Pile)

Max Activating Token Index: 35