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

Dataset: The Pile

Neuron 3092 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: 0.7397. Min Range: -0.7397

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1677058 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7397. Min Act: -0.0000

Data Index: 197241 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6009. Min Act: -0.0000

Data Index: 901619 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6916. Min Act: 0.0000

Data Index: 1504331 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6422. Min Act: -0.0000

Data Index: 797470 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6246. Min Act: -0.0000

Data Index: 845073 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6406. Min Act: -0.0000

Data Index: 419249 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1752980 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1461335 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6265. Min Act: -0.0000

Data Index: 818442 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6042. Min Act: -0.0000

Data Index: 970981 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1257301 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1488529 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6310. Min Act: 0.0000

Data Index: 288675 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1491211 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5730. Min Act: -0.0000

Data Index: 323029 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1124066 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1605933 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1478547 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1354962 (The Pile)

Max Activating Token Index: 997