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

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

Neuron 4666 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: 2.6597. Min Range: -2.6597

Max Act: 2.5775. Min Act: -0.0000

Data Index: 378047 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.6597. Min Act: -0.0000

Data Index: 772230 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.4076. Min Act: -0.0000

Data Index: 529568 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.4777. Min Act: -0.0000

Data Index: 703516 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.4659. Min Act: -0.0000

Data Index: 211584 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2674. Min Act: -0.0000

Data Index: 385802 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2909. Min Act: -0.0000

Data Index: 584320 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2866. Min Act: -0.0000

Data Index: 69776 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1291540 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3730. Min Act: -0.0000

Data Index: 972590 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3667. Min Act: -0.0000

Data Index: 388537 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3312. Min Act: -0.0000

Data Index: 596347 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.3324. Min Act: -0.0000

Data Index: 841478 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.5295. Min Act: -0.0000

Data Index: 198214 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2863. Min Act: -0.0000

Data Index: 292156 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2658. Min Act: -0.0000

Data Index: 1183126 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2461. Min Act: -0.0000

Data Index: 1097706 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.1322. Min Act: -0.0000

Data Index: 44410 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2502. Min Act: -0.0000

Data Index: 47039 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.6597. Min Range: -2.6597

Max Act: 2.2583. Min Act: -0.0000

Data Index: 79939 (C4 (Web Text))

Max Activating Token Index: 612