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

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

Neuron 2683 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1153. Min Act: -0.0003

Data Index: 753653 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1101. Min Act: -0.0003

Data Index: 43647 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1162. Min Act: -0.0003

Data Index: 1349213 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1154. Min Act: -0.0003

Data Index: 397807 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1047. Min Act: -0.0003

Data Index: 447977 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1037. Min Act: -0.0003

Data Index: 212107 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1006. Min Act: -0.0003

Data Index: 261470 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1106. Min Act: -0.0003

Data Index: 1276496 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1022. Min Act: -0.0003

Data Index: 179503 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1100. Min Act: -0.0003

Data Index: 76671 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1021. Min Act: -0.0003

Data Index: 1267506 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0983. Min Act: -0.0003

Data Index: 781284 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1050. Min Act: -0.0003

Data Index: 267573 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1018. Min Act: -0.0003

Data Index: 65317 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1047. Min Act: -0.0003

Data Index: 157197 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1050. Min Act: -0.0003

Data Index: 817781 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1008. Min Act: -0.0003

Data Index: 467156 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1031. Min Act: -0.0003

Data Index: 539188 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0998. Min Act: -0.0003

Data Index: 77853 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1247023 (C4 (Web Text))

Max Activating Token Index: 149