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

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

Neuron 1623 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: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0001

Data Index: 149602 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1074. Min Act: -0.0001

Data Index: 315826 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1137. Min Act: -0.0001

Data Index: 39134 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1290553 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1037460 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1007. Min Act: -0.0001

Data Index: 762521 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0997. Min Act: -0.0001

Data Index: 573240 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0966. Min Act: -0.0001

Data Index: 795452 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1021. Min Act: -0.0001

Data Index: 99608 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1107155 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0974. Min Act: -0.0001

Data Index: 627396 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1187737 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0892. Min Act: -0.0001

Data Index: 446152 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0954. Min Act: -0.0001

Data Index: 335505 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1166583 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0860. Min Act: -0.0001

Data Index: 872456 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0930. Min Act: -0.0001

Data Index: 2702 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0941. Min Act: -0.0001

Data Index: 25244 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0851. Min Act: -0.0001

Data Index: 132268 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0888. Min Act: -0.0001

Data Index: 608878 (C4 (Web Text))

Max Activating Token Index: 156