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

Dataset: The Pile

Neuron 3406 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: 0.9458. Min Range: -0.9458

Max Act: 0.9458. Min Act: -0.0000

Data Index: 736237 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8324. Min Act: -0.0000

Data Index: 94546 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1851355 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1859580 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7024. Min Act: -0.0000

Data Index: 934940 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1600228 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7495. Min Act: -0.0000

Data Index: 847066 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7075. Min Act: -0.0000

Data Index: 635555 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7082. Min Act: -0.0000

Data Index: 666504 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1416998 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1966158 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6729. Min Act: -0.0000

Data Index: 371864 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1786295 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1254220 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1306881 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6766. Min Act: -0.0000

Data Index: 181912 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6468. Min Act: -0.0000

Data Index: 947147 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1575019 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6422. Min Act: -0.0000

Data Index: 224003 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6355. Min Act: -0.0000

Data Index: 211674 (The Pile)

Max Activating Token Index: 550