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

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

Neuron 798 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0921. Min Range: -2.0921

Max Act: 2.0921. Min Act: -0.0000

Data Index: 125021 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.9406. Min Act: -0.0000

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.5859. Min Act: -0.0000

Data Index: 757257 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.6673. Min Act: -0.0000

Data Index: 980796 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1115860 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1615423 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.5015. Min Act: -0.0000

Data Index: 986490 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1415179 (Python Code)

Max Activating Token Index: 817

Text #8

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.4356. Min Act: -0.0000

Data Index: 721453 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.4355. Min Act: -0.0000

Data Index: 53738 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1520671 (Python Code)

Max Activating Token Index: 857

Text #11

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1150200 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.3593. Min Act: -0.0000

Data Index: 413678 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1442923 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.2398. Min Act: -0.0000

Data Index: 308667 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.1929. Min Act: -0.0000

Data Index: 89346 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.1429. Min Act: 0.0000

Data Index: 277061 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.0735. Min Act: -0.0000

Data Index: 309412 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1324360 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 2.0921. Min Range: -2.0921

Max Act: 1.0499. Min Act: -0.0000

Data Index: 928795 (C4 (Web Text))

Max Activating Token Index: 315