Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1981 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1484702 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0005

Data Index: 566098 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1623450 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0105. Min Act: -0.0006

Data Index: 105223 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1259113 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0097. Min Act: -0.0006

Data Index: 246334 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0100. Min Act: -0.0006

Data Index: 699385 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0098. Min Act: -0.0006

Data Index: 325899 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0096. Min Act: -0.0006

Data Index: 237610 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0097. Min Act: -0.0005

Data Index: 708431 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0096. Min Act: -0.0006

Data Index: 31428 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0095. Min Act: -0.0006

Data Index: 118774 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0095. Min Act: -0.0006

Data Index: 581589 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0093. Min Act: -0.0006

Data Index: 985730 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1080486 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0090. Min Act: -0.0006

Data Index: 763597 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0093. Min Act: -0.0006

Data Index: 158943 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1126739 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1395238 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0090. Min Act: -0.0006

Data Index: 422650 (C4 (Web Text))

Max Activating Token Index: 744