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

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

Neuron 884 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.3250. Min Act: -0.0001

Data Index: 296331 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.1720. Min Act: -0.0001

Data Index: 62821 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.1447. Min Act: -0.0001

Data Index: 1137300 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0652. Min Act: -0.0001

Data Index: 733829 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0855. Min Act: -0.0001

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0514. Min Act: -0.0001

Data Index: 198022 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9461. Min Act: -0.0001

Data Index: 1235191 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0044. Min Act: -0.0001

Data Index: 243257 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0627. Min Act: -0.0001

Data Index: 1609782 (Python Code)

Max Activating Token Index: 488

Text #9

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0520. Min Act: -0.0001

Data Index: 257161 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9608. Min Act: -0.0001

Data Index: 1561292 (Python Code)

Max Activating Token Index: 561

Text #11

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0201. Min Act: -0.0001

Data Index: 1019965 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9530. Min Act: -0.0001

Data Index: 342392 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9875. Min Act: -0.0001

Data Index: 153273 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9529. Min Act: -0.0001

Data Index: 156228 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9791. Min Act: -0.0001

Data Index: 1251973 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9449. Min Act: -0.0001

Data Index: 785419 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9135. Min Act: -0.0001

Data Index: 1328619 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.0166. Min Act: -0.0001

Data Index: 368247 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.9840. Min Act: -0.0001

Data Index: 644145 (C4 (Web Text))

Max Activating Token Index: 730