Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2805 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0760. Min Act: -0.0000

Data Index: 404892 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0632. Min Act: -0.0000

Data Index: 945199 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9298. Min Act: -0.0000

Data Index: 122223 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0510. Min Act: -0.0000

Data Index: 36145 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9601. Min Act: -0.0000

Data Index: 938450 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0270. Min Act: -0.0000

Data Index: 74705 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9640. Min Act: -0.0000

Data Index: 456754 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9265. Min Act: -0.0000

Data Index: 235453 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9569. Min Act: -0.0000

Data Index: 755712 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1098052 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8958. Min Act: -0.0000

Data Index: 192431 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8987. Min Act: -0.0000

Data Index: 887603 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9020. Min Act: 0.0000

Data Index: 1271547 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8907. Min Act: -0.0000

Data Index: 975242 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1158020 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8615. Min Act: -0.0000

Data Index: 573154 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8369. Min Act: -0.0000

Data Index: 379687 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8555. Min Act: -0.0000

Data Index: 758164 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8761. Min Act: -0.0000

Data Index: 879424 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8510. Min Act: -0.0000

Data Index: 306408 (C4 (Web Text))

Max Activating Token Index: 671