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

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

Neuron 11 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: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0006

Data Index: 18499 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0641. Min Act: -0.0005

Data Index: 254319 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0620. Min Act: -0.0006

Data Index: 1259975 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0595. Min Act: -0.0006

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0585. Min Act: -0.0005

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0577. Min Act: -0.0006

Data Index: 1145709 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0571. Min Act: -0.0006

Data Index: 1322197 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0557. Min Act: -0.0005

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0558. Min Act: -0.0006

Data Index: 180049 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0556. Min Act: -0.0006

Data Index: 367599 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0555. Min Act: -0.0006

Data Index: 1237850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0552. Min Act: -0.0006

Data Index: 890801 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0539. Min Act: -0.0006

Data Index: 466568 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0527. Min Act: -0.0005

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0542. Min Act: -0.0006

Data Index: 699994 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0513. Min Act: -0.0005

Data Index: 891250 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0496. Min Act: -0.0005

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0496. Min Act: -0.0006

Data Index: 346515 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0504. Min Act: -0.0005

Data Index: 1234973 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0504. Min Act: -0.0006

Data Index: 268682 (C4 (Web Text))

Max Activating Token Index: 116