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

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

Neuron 2933 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1303440 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0133. Min Act: -0.0003

Data Index: 762287 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0003

Data Index: 2998 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0003

Data Index: 664090 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1045308 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1193236 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0123. Min Act: -0.0003

Data Index: 116280 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1295877 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1017643 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0122. Min Act: -0.0003

Data Index: 163862 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0003

Data Index: 646104 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0121. Min Act: -0.0003

Data Index: 120060 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0123. Min Act: -0.0003

Data Index: 5493 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0121. Min Act: -0.0003

Data Index: 596773 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0119. Min Act: -0.0003

Data Index: 760931 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0118. Min Act: -0.0003

Data Index: 823399 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0120. Min Act: -0.0003

Data Index: 56957 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1187111 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0114. Min Act: -0.0003

Data Index: 610435 (C4 (Web Text))

Max Activating Token Index: 597