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

Dataset: The Pile

Neuron 4006 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4900. Min Act: -0.0000

Data Index: 228062 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1343399 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1195162 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1927488 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4533. Min Act: 0.0000

Data Index: 1017245 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1026028 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4136. Min Act: -0.0000

Data Index: 281921 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1634579 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4318. Min Act: -0.0000

Data Index: 276504 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4290. Min Act: -0.0000

Data Index: 950972 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4150. Min Act: -0.0000

Data Index: 112995 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1872119 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3982. Min Act: -0.0000

Data Index: 317519 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4357. Min Act: -0.0000

Data Index: 54515 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4194. Min Act: -0.0000

Data Index: 761236 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1948442 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3862. Min Act: -0.0000

Data Index: 304895 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3841. Min Act: -0.0000

Data Index: 346770 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1737028 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1354193 (The Pile)

Max Activating Token Index: 362