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

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

Neuron 3669 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5968. Min Act: -0.0000

Data Index: 918204 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5517. Min Act: -0.0000

Data Index: 970483 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5092. Min Act: 0.0001

Data Index: 1307789 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4878. Min Act: -0.0000

Data Index: 38336 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4868. Min Act: -0.0000

Data Index: 367718 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4986. Min Act: -0.0000

Data Index: 637151 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4673. Min Act: -0.0000

Data Index: 131264 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4806. Min Act: 0.0000

Data Index: 690496 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4762. Min Act: -0.0000

Data Index: 613226 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4641. Min Act: 0.0001

Data Index: 106482 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4360. Min Act: -0.0000

Data Index: 120460 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4498. Min Act: -0.0000

Data Index: 418438 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4592. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4237. Min Act: -0.0000

Data Index: 353088 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1169216 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4157. Min Act: 0.0000

Data Index: 194157 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1172405 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1279325 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.3981. Min Act: -0.0000

Data Index: 982097 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4178. Min Act: -0.0000

Data Index: 565508 (C4 (Web Text))

Max Activating Token Index: 731