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

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

Neuron 2401 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6933. Min Act: -0.0000

Data Index: 700067 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6769. Min Act: -0.0000

Data Index: 325787 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6562. Min Act: -0.0000

Data Index: 246472 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1242502 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6283. Min Act: -0.0000

Data Index: 560772 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5719. Min Act: -0.0000

Data Index: 64088 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5742. Min Act: -0.0000

Data Index: 493103 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1301999 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5644. Min Act: -0.0000

Data Index: 593262 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1096018 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5563. Min Act: -0.0000

Data Index: 913393 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1159787 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5109. Min Act: -0.0000

Data Index: 866887 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1044982 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5060. Min Act: -0.0000

Data Index: 185565 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1277756 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5127. Min Act: -0.0000

Data Index: 909407 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5096. Min Act: -0.0000

Data Index: 439098 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4865. Min Act: -0.0000

Data Index: 188998 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1334628 (C4 (Web Text))

Max Activating Token Index: 300