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

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

Neuron 26 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: 1335608 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1409000 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0004

Data Index: 1314250 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 343795 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 693595 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 936713 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 947822 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 998805 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1073590 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 278888 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 748274 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0004

Data Index: 631346 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 18648 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1156894 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 912255 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 518868 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 886371 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 800983 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 805168 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 213958 (C4 (Web Text))

Max Activating Token Index: 618