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

Dataset: The Pile

Neuron 3209 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8966. Min Act: -0.0000

Data Index: 407374 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8721. Min Act: -0.0000

Data Index: 537007 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1410400 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7778. Min Act: -0.0000

Data Index: 986923 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1131527 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7824. Min Act: -0.0000

Data Index: 503924 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1397187 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1043988 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7677. Min Act: -0.0000

Data Index: 400411 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7615. Min Act: -0.0000

Data Index: 293191 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1473373 (The Pile)

Max Activating Token Index: 959

Text #11

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1150329 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7121. Min Act: -0.0000

Data Index: 71795 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1404819 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1147154 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1342455 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7366. Min Act: -0.0000

Data Index: 251584 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1952617 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7052. Min Act: -0.0000

Data Index: 108394 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1257822 (The Pile)

Max Activating Token Index: 293