Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4857 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2093. Min Range: -1.2093

Max Act: 1.0566. Min Act: -0.0000

Data Index: 448827 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 1.2093. Min Range: -1.2093

Max Act: 1.0176. Min Act: -0.0000

Data Index: 535139 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8729. Min Act: -0.0000

Data Index: 142541 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1187120 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1288831 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1142628 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1054414 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 1.2093. Min Range: -1.2093

Max Act: 1.2093. Min Act: -0.0000

Data Index: 478439 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8292. Min Act: -0.0000

Data Index: 389131 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8569. Min Act: -0.0000

Data Index: 763168 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1068464 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1264635 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8135. Min Act: -0.0000

Data Index: 557104 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1286588 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8318. Min Act: -0.0000

Data Index: 133167 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.8487. Min Act: -0.0000

Data Index: 512964 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.7620. Min Act: -0.0000

Data Index: 407412 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.7539. Min Act: -0.0000

Data Index: 167705 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.7584. Min Act: -0.0000

Data Index: 842208 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.2093. Min Range: -1.2093

Max Act: 0.7079. Min Act: -0.0000

Data Index: 567792 (C4 (Web Text))

Max Activating Token Index: 600