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

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

Neuron 1276 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6826. Min Act: -0.0001

Data Index: 948901 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6063. Min Act: -0.0000

Data Index: 9528 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5969. Min Act: -0.0000

Data Index: 857059 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5641. Min Act: -0.0000

Data Index: 573784 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1312875 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4957. Min Act: -0.0000

Data Index: 39523 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5064. Min Act: -0.0000

Data Index: 451238 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4851. Min Act: -0.0000

Data Index: 298392 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4742. Min Act: -0.0001

Data Index: 950303 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4535. Min Act: -0.0001

Data Index: 1110346 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1358758 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4470. Min Act: -0.0000

Data Index: 74956 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4566. Min Act: -0.0000

Data Index: 903378 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4386. Min Act: -0.0000

Data Index: 335151 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4683. Min Act: -0.0001

Data Index: 152926 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4522. Min Act: -0.0000

Data Index: 625942 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4328. Min Act: -0.0000

Data Index: 422314 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4480. Min Act: -0.0001

Data Index: 422449 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4485. Min Act: -0.0001

Data Index: 489732 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4472. Min Act: -0.0001

Data Index: 112429 (C4 (Web Text))

Max Activating Token Index: 153