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

Dataset: The Pile

Neuron 2476 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: 0.2870. Min Range: -0.2870

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1241938 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1196241 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1952794 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2224. Min Act: -0.0000

Data Index: 287718 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2263. Min Act: -0.0000

Data Index: 167468 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1954897 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2391. Min Act: -0.0000

Data Index: 520722 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1127119 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1861. Min Act: -0.0000

Data Index: 814966 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1976. Min Act: -0.0000

Data Index: 601943 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1427402 (The Pile)

Max Activating Token Index: 235

Text #11

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1717320 (The Pile)

Max Activating Token Index: 672

Text #12

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1972962 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1646114 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1915321 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1637562 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1706. Min Act: -0.0000

Data Index: 73630 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1470916 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1934. Min Act: -0.0000

Data Index: 815214 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1598. Min Act: -0.0000

Data Index: 66191 (The Pile)

Max Activating Token Index: 630