Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.7588. Min Act: -0.0001

Data Index: 401278 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1093371 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.5546. Min Act: -0.0000

Data Index: 697830 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.5423. Min Act: -0.0001

Data Index: 774661 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4987. Min Act: -0.0001

Data Index: 1357649 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4856. Min Act: -0.0001

Data Index: 107201 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1045040 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4962. Min Act: -0.0001

Data Index: 1173191 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4302. Min Act: -0.0001

Data Index: 247210 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4570. Min Act: -0.0001

Data Index: 1117909 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4493. Min Act: -0.0001

Data Index: 263129 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.2469. Min Act: -0.0001

Data Index: 471094 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.4207. Min Act: -0.0000

Data Index: 476951 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.3339. Min Act: -0.0001

Data Index: 1328229 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.2879. Min Act: -0.0001

Data Index: 1244131 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.2376. Min Act: -0.0001

Data Index: 1112528 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.3632. Min Act: -0.0001

Data Index: 9150 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.2820. Min Act: -0.0001

Data Index: 992922 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.2789. Min Act: -0.0000

Data Index: 362241 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.7588. Min Range: -1.7588

Max Act: 1.3427. Min Act: -0.0001

Data Index: 186165 (C4 (Web Text))

Max Activating Token Index: 486