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

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

Neuron 1128 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: -0.0004

Data Index: 1264196 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 146520 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1395643 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1575814 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1445290 (Python Code)

Max Activating Token Index: 346

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 419274 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1447813 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 119518 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1399178 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1520235 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1646315 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1638506 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1652367 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1488457 (Python Code)

Max Activating Token Index: 210

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1632305 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1612770 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0004

Data Index: 1575660 (Python Code)

Max Activating Token Index: 122

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1395764 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1546070 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1066388 (C4 (Web Text))

Max Activating Token Index: 41