Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1514 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0006

Data Index: 1298550 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0552. Min Act: -0.0006

Data Index: 366933 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0540. Min Act: -0.0006

Data Index: 788888 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0554. Min Act: -0.0006

Data Index: 609785 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0569. Min Act: -0.0006

Data Index: 7229 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0558. Min Act: -0.0006

Data Index: 1028193 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0546. Min Act: -0.0006

Data Index: 612190 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0556. Min Act: -0.0006

Data Index: 582179 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0548. Min Act: -0.0006

Data Index: 274754 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0494. Min Act: -0.0006

Data Index: 396132 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0548. Min Act: -0.0006

Data Index: 945594 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0511. Min Act: -0.0006

Data Index: 403331 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0545. Min Act: -0.0006

Data Index: 196624 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0546. Min Act: -0.0006

Data Index: 1020247 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0524. Min Act: -0.0006

Data Index: 1012412 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0534. Min Act: -0.0006

Data Index: 96094 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0544. Min Act: -0.0006

Data Index: 186368 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0531. Min Act: -0.0006

Data Index: 266281 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0510. Min Act: -0.0006

Data Index: 79606 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1319255 (C4 (Web Text))

Max Activating Token Index: 571