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

Dataset: The Pile

Neuron 4829 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.5929. Min Act: -0.0000

Data Index: 600767 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.5351. Min Act: -0.0000

Data Index: 720976 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.5084. Min Act: -0.0000

Data Index: 628325 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.4044. Min Act: -0.0000

Data Index: 154232 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.4805. Min Act: -0.0000

Data Index: 332867 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.1359. Min Act: 0.0000

Data Index: 1174386 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.0405. Min Act: -0.0000

Data Index: 589289 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.9809. Min Act: -0.0000

Data Index: 1980396 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.7377. Min Act: -0.0000

Data Index: 37668 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.0079. Min Act: -0.0000

Data Index: 1307152 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.9676. Min Act: -0.0000

Data Index: 292300 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.6485. Min Act: -0.0000

Data Index: 1501411 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.8482. Min Act: 0.0000

Data Index: 1085167 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.8988. Min Act: -0.0000

Data Index: 880635 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.7007. Min Act: -0.0000

Data Index: 1263310 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 3.5929. Min Range: -3.5929

Max Act: 3.0887. Min Act: -0.0000

Data Index: 1192411 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.8433. Min Act: -0.0000

Data Index: 1129828 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.8739. Min Act: -0.0000

Data Index: 1377882 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.4709. Min Act: -0.0000

Data Index: 1635448 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 3.5929. Min Range: -3.5929

Max Act: 2.6664. Min Act: -0.0000

Data Index: 1125864 (The Pile)

Max Activating Token Index: 61