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

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

Neuron 2612 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: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0004

Data Index: 763285 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0003

Data Index: 181986 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 470541 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0003

Data Index: 120310 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0004

Data Index: 239010 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1109617 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0120. Min Act: -0.0003

Data Index: 273491 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0117. Min Act: -0.0003

Data Index: 472602 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0004

Data Index: 839689 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0003

Data Index: 359551 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1207605 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0108. Min Act: -0.0003

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0107. Min Act: -0.0003

Data Index: 339130 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0104. Min Act: -0.0003

Data Index: 291618 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1344974 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0103. Min Act: -0.0003

Data Index: 655985 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1170836 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1608203 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0102. Min Act: -0.0003

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1282358 (C4 (Web Text))

Max Activating Token Index: 930