Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3124. Min Range: -1.3124

Max Act: 1.3124. Min Act: -0.0000

Data Index: 595394 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.3124. Min Range: -1.3124

Max Act: 1.1323. Min Act: -0.0000

Data Index: 798286 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9658. Min Act: -0.0000

Data Index: 253795 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9926. Min Act: -0.0000

Data Index: 247545 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9186. Min Act: -0.0000

Data Index: 900596 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9878. Min Act: -0.0000

Data Index: 13091 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9148. Min Act: -0.0000

Data Index: 905993 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.8976. Min Act: -0.0000

Data Index: 59893 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.8676. Min Act: -0.0000

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9075. Min Act: -0.0000

Data Index: 853208 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1088068 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9168. Min Act: -0.0000

Data Index: 678951 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1262759 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1021101 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1047973 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7917. Min Act: -0.0000

Data Index: 550515 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7845. Min Act: -0.0000

Data Index: 196787 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1153590 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7542. Min Act: -0.0000

Data Index: 506354 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7938. Min Act: -0.0000

Data Index: 941523 (C4 (Web Text))

Max Activating Token Index: 503