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

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

Neuron 4122 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.7922. Min Act: -0.0000

Data Index: 1303468 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.3825. Min Act: -0.0000

Data Index: 937109 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 4.7922. Min Range: -4.7922

Max Act: 4.1992. Min Act: -0.0000

Data Index: 830227 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.6133. Min Act: -0.0000

Data Index: 391175 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.3162. Min Act: -0.0000

Data Index: 503391 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.3139. Min Act: -0.0000

Data Index: 1232653 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.2209. Min Act: -0.0000

Data Index: 1083735 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.2284. Min Act: -0.0000

Data Index: 8509 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.0068. Min Act: -0.0000

Data Index: 208675 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.1266. Min Act: -0.0000

Data Index: 41398 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.2442. Min Act: -0.0000

Data Index: 1011896 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 4.7922. Min Range: -4.7922

Max Act: 3.0341. Min Act: -0.0000

Data Index: 2148 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.8654. Min Act: -0.0000

Data Index: 311726 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.9802. Min Act: -0.0000

Data Index: 282231 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.9457. Min Act: -0.0000

Data Index: 855004 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.9096. Min Act: -0.0000

Data Index: 873321 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.7470. Min Act: -0.0000

Data Index: 334333 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.8931. Min Act: -0.0000

Data Index: 805413 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.7533. Min Act: -0.0000

Data Index: 197017 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 4.7922. Min Range: -4.7922

Max Act: 2.8699. Min Act: -0.0000

Data Index: 1349905 (C4 (Web Text))

Max Activating Token Index: 545