Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 461 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5883. Min Act: -0.0001

Data Index: 842531 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5728. Min Act: -0.0001

Data Index: 287161 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5561. Min Act: -0.0001

Data Index: 809648 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5888. Min Act: -0.0001

Data Index: 45026 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5358. Min Act: -0.0001

Data Index: 192283 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5353. Min Act: -0.0001

Data Index: 396212 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5659. Min Act: -0.0001

Data Index: 942453 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5439. Min Act: -0.0001

Data Index: 111322 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5124. Min Act: -0.0001

Data Index: 2778 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5263. Min Act: -0.0001

Data Index: 1027854 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5152. Min Act: -0.0001

Data Index: 815288 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5091. Min Act: -0.0001

Data Index: 12861 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5092. Min Act: -0.0001

Data Index: 146668 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4917. Min Act: -0.0001

Data Index: 714324 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4900. Min Act: -0.0001

Data Index: 1195292 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4876. Min Act: -0.0001

Data Index: 1151827 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5176. Min Act: -0.0001

Data Index: 761232 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5197. Min Act: -0.0001

Data Index: 583065 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.5029. Min Act: -0.0001

Data Index: 1195392 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.5888. Min Range: -0.5888

Max Act: 0.4954. Min Act: -0.0001

Data Index: 1091966 (C4 (Web Text))

Max Activating Token Index: 140