Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5965 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3835. Min Range: -4.3835

Max Act: 4.3835. Min Act: -0.0000

Data Index: 1077545 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 4.3835. Min Range: -4.3835

Max Act: 3.2688. Min Act: -0.0000

Data Index: 1185684 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 4.3835. Min Range: -4.3835

Max Act: 3.0427. Min Act: -0.0000

Data Index: 455363 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.8735. Min Act: -0.0000

Data Index: 466535 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.6653. Min Act: -0.0000

Data Index: 1117311 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.6009. Min Act: -0.0000

Data Index: 514558 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.7377. Min Act: -0.0000

Data Index: 359642 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.4654. Min Act: -0.0000

Data Index: 1625116 (Python Code)

Max Activating Token Index: 620

Text #8

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.5405. Min Act: -0.0000

Data Index: 1047860 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.3549. Min Act: -0.0000

Data Index: 583052 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.3046. Min Act: -0.0000

Data Index: 872450 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.0621. Min Act: -0.0000

Data Index: 519782 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.1479. Min Act: -0.0000

Data Index: 478411 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.1426. Min Act: -0.0000

Data Index: 6040 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.0027. Min Act: -0.0000

Data Index: 710675 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.0814. Min Act: -0.0000

Data Index: 115368 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.0637. Min Act: -0.0000

Data Index: 711081 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 4.3835. Min Range: -4.3835

Max Act: 2.0610. Min Act: -0.0000

Data Index: 393139 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 4.3835. Min Range: -4.3835

Max Act: 1.9192. Min Act: -0.0000

Data Index: 937248 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 4.3835. Min Range: -4.3835

Max Act: 1.9863. Min Act: -0.0000

Data Index: 666642 (C4 (Web Text))

Max Activating Token Index: 292