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

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

Neuron 4466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0001

Data Index: 1006045 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1173. Min Act: -0.0001

Data Index: 1079190 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9888. Min Act: -0.0000

Data Index: 514883 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1242066 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9311. Min Act: -0.0000

Data Index: 84 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1187479 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9625. Min Act: -0.0000

Data Index: 179721 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9186. Min Act: -0.0000

Data Index: 278034 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8950. Min Act: -0.0001

Data Index: 567305 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9345. Min Act: -0.0000

Data Index: 812592 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8630. Min Act: -0.0000

Data Index: 867920 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8897. Min Act: -0.0001

Data Index: 1001764 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8716. Min Act: -0.0001

Data Index: 749613 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8762. Min Act: -0.0000

Data Index: 812580 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7902. Min Act: -0.0000

Data Index: 792429 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1158652 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8101. Min Act: -0.0001

Data Index: 909640 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7953. Min Act: -0.0001

Data Index: 47260 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8183. Min Act: -0.0001

Data Index: 828932 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1133442 (C4 (Web Text))

Max Activating Token Index: 157