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

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

Neuron 1237 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: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0006

Data Index: 72370 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1374772 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0491. Min Act: -0.0006

Data Index: 765073 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0484. Min Act: -0.0006

Data Index: 369670 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0473. Min Act: -0.0006

Data Index: 1630985 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0475. Min Act: -0.0006

Data Index: 318321 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0477. Min Act: -0.0006

Data Index: 358455 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0488. Min Act: -0.0006

Data Index: 71405 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1479269 (Python Code)

Max Activating Token Index: 931

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0432. Min Act: -0.0006

Data Index: 1529195 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0460. Min Act: -0.0006

Data Index: 527973 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1108702 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0511. Min Act: -0.0006

Data Index: 903878 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0496. Min Act: -0.0006

Data Index: 857348 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0486. Min Act: -0.0006

Data Index: 1600709 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1340926 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0442. Min Act: -0.0006

Data Index: 1644130 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0458. Min Act: -0.0006

Data Index: 1277042 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1586398 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0456. Min Act: -0.0006

Data Index: 1622823 (Python Code)

Max Activating Token Index: 974