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

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

Neuron 2130 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4597. Min Act: -0.0000

Data Index: 841147 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3801. Min Act: -0.0000

Data Index: 719610 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3408. Min Act: -0.0000

Data Index: 274005 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3397. Min Act: -0.0000

Data Index: 590054 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3124. Min Act: -0.0000

Data Index: 739495 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1206406 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3059. Min Act: -0.0000

Data Index: 417997 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2715. Min Act: -0.0000

Data Index: 324875 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1212134 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2766. Min Act: -0.0000

Data Index: 384790 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2731. Min Act: -0.0000

Data Index: 51941 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2828. Min Act: -0.0000

Data Index: 257889 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2710. Min Act: -0.0000

Data Index: 143071 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1166186 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2694. Min Act: -0.0000

Data Index: 307198 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1226220 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2617. Min Act: -0.0000

Data Index: 511828 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2757. Min Act: -0.0000

Data Index: 210705 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2743. Min Act: -0.0000

Data Index: 86364 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1229077 (C4 (Web Text))

Max Activating Token Index: 246