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

Dataset: The Pile

Neuron 1480 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1385310 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1843701 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1073448 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1091328 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1731558 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2503. Min Act: -0.0000

Data Index: 172713 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2154. Min Act: -0.0000

Data Index: 496665 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1914442 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2231. Min Act: -0.0000

Data Index: 126565 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2186. Min Act: -0.0000

Data Index: 171348 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1212275 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2216. Min Act: -0.0000

Data Index: 189669 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1970. Min Act: -0.0000

Data Index: 710063 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1174354 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1872347 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2064. Min Act: -0.0000

Data Index: 462625 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1974. Min Act: -0.0000

Data Index: 191127 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2197. Min Act: -0.0000

Data Index: 89964 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1611420 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2087. Min Act: -0.0000

Data Index: 844735 (The Pile)

Max Activating Token Index: 950