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

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

Neuron 3299 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0002

Data Index: 148962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0141. Min Act: -0.0002

Data Index: 107058 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0126. Min Act: -0.0002

Data Index: 587902 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0109. Min Act: -0.0002

Data Index: 551010 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0118. Min Act: -0.0002

Data Index: 288813 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1600481 (Python Code)

Max Activating Token Index: 913

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0124. Min Act: -0.0002

Data Index: 120026 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0117. Min Act: -0.0002

Data Index: 999826 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1430273 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0104. Min Act: -0.0002

Data Index: 857316 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0110. Min Act: -0.0002

Data Index: 928453 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0108. Min Act: -0.0002

Data Index: 192206 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1436135 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0110. Min Act: -0.0002

Data Index: 320037 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0143. Min Act: -0.0002

Data Index: 592599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1494467 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0110. Min Act: -0.0002

Data Index: 708761 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0099. Min Act: -0.0002

Data Index: 705095 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1264066 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0105. Min Act: -0.0002

Data Index: 695825 (C4 (Web Text))

Max Activating Token Index: 27