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

Dataset: The Pile

Neuron 1220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1870605 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.7270. Min Act: 0.0000

Data Index: 852650 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6766. Min Act: -0.0000

Data Index: 423491 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1121788 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6976. Min Act: -0.0000

Data Index: 71654 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1154478 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6562. Min Act: -0.0000

Data Index: 21857 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1235236 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1816933 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1736253 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1914510 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1971950 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6108. Min Act: 0.0000

Data Index: 1323382 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1024897 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1035722 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1206305 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1604819 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1639944 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5949. Min Act: 0.0000

Data Index: 583585 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.6158. Min Act: 0.0000

Data Index: 483100 (The Pile)

Max Activating Token Index: 180