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

Dataset: The Pile

Neuron 3929 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.7121. Min Act: -0.0000

Data Index: 585059 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6488. Min Act: -0.0000

Data Index: 1409705 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.3777. Min Act: -0.0000

Data Index: 204315 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1119252 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.3553. Min Act: -0.0000

Data Index: 9059 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.4503. Min Act: -0.0000

Data Index: 603714 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.5270. Min Act: -0.0000

Data Index: 873160 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.4864. Min Act: -0.0000

Data Index: 71103 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.2707. Min Act: -0.0000

Data Index: 692897 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1419. Min Act: -0.0000

Data Index: 297255 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1544388 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1827459 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1874. Min Act: -0.0000

Data Index: 501178 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1735343 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1979285 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1126974 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1463119 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1425. Min Act: -0.0000

Data Index: 546364 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1096410 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.1290. Min Act: -0.0000

Data Index: 473990 (The Pile)

Max Activating Token Index: 762