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

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

Neuron 929 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: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 616795 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1219047 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 532951 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 35251 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 633081 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1320913 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1003643 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1212358 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 182686 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 515346 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 169135 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1163353 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 153236 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 206209 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1139883 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1049275 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 438543 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 367865 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1228677 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1203842 (C4 (Web Text))

Max Activating Token Index: 137