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

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

Neuron 105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.6063. Min Act: -0.0000

Data Index: 644122 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.6023. Min Act: -0.0000

Data Index: 268817 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1227072 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5600. Min Act: -0.0001

Data Index: 1323765 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1261253 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5374. Min Act: -0.0000

Data Index: 240737 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5237. Min Act: -0.0000

Data Index: 6935 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4834. Min Act: -0.0000

Data Index: 404682 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4866. Min Act: -0.0000

Data Index: 923519 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4829. Min Act: -0.0001

Data Index: 614451 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4873. Min Act: -0.0000

Data Index: 291724 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1315010 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5018. Min Act: -0.0000

Data Index: 339228 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1130444 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4925. Min Act: -0.0000

Data Index: 684446 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1142873 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4714. Min Act: -0.0000

Data Index: 509161 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4785. Min Act: -0.0000

Data Index: 414220 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4760. Min Act: -0.0000

Data Index: 520462 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4932. Min Act: -0.0000

Data Index: 235808 (C4 (Web Text))

Max Activating Token Index: 606