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

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

Neuron 2136 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: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1398096 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1602757 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1397419 (Python Code)

Max Activating Token Index: 934

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0003

Data Index: 994203 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0004

Data Index: 1318515 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1085395 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1592872 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0003

Data Index: 900149 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1638060 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1508011 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1422377 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1286314 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1368716 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1645623 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1399117 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1395212 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1652144 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1555227 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0003

Data Index: 2682 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1081563 (C4 (Web Text))

Max Activating Token Index: 216