Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3709 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1301774 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1269541 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0003

Data Index: 107164 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1302833 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0003

Data Index: 240945 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0131. Min Act: -0.0003

Data Index: 613640 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0003

Data Index: 440417 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0003

Data Index: 133955 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0003

Data Index: 876478 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1097799 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 617270 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1090222 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 880903 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 852068 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0003

Data Index: 189286 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1319628 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 870101 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1053671 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0003

Data Index: 700702 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0003

Data Index: 704733 (C4 (Web Text))

Max Activating Token Index: 49