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

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

Neuron 3538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.6874. Min Act: -0.0000

Data Index: 96663 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1235614 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1104660 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4949. Min Act: -0.0000

Data Index: 322976 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5171. Min Act: -0.0000

Data Index: 733039 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.5055. Min Act: -0.0000

Data Index: 939297 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4551. Min Act: -0.0000

Data Index: 979108 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4695. Min Act: -0.0000

Data Index: 998872 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4809. Min Act: -0.0000

Data Index: 951275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1274739 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1244196 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4756. Min Act: -0.0000

Data Index: 874361 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4608. Min Act: -0.0000

Data Index: 956338 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4482. Min Act: -0.0000

Data Index: 343900 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4461. Min Act: -0.0000

Data Index: 82406 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4627. Min Act: -0.0000

Data Index: 663463 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1092344 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4484. Min Act: -0.0000

Data Index: 314656 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4200. Min Act: -0.0000

Data Index: 129202 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.6874. Min Range: -0.6874

Max Act: 0.4131. Min Act: -0.0000

Data Index: 579618 (C4 (Web Text))

Max Activating Token Index: 613