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

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

Neuron 2760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6430. Min Range: -2.6430

Max Act: 2.6430. Min Act: -0.0000

Data Index: 1249493 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 2.6430. Min Range: -2.6430

Max Act: 2.4886. Min Act: -0.0000

Data Index: 35925 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 2.6430. Min Range: -2.6430

Max Act: 2.5471. Min Act: -0.0000

Data Index: 398150 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 2.6430. Min Range: -2.6430

Max Act: 2.2630. Min Act: -0.0000

Data Index: 227905 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.9750. Min Act: -0.0000

Data Index: 270673 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.7561. Min Act: -0.0000

Data Index: 957935 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.9655. Min Act: -0.0000

Data Index: 461607 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.8698. Min Act: -0.0000

Data Index: 1295809 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.7989. Min Act: -0.0000

Data Index: 280458 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1072000 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.5780. Min Act: -0.0000

Data Index: 12664 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.7372. Min Act: -0.0000

Data Index: 280578 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.6343. Min Act: -0.0000

Data Index: 661163 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1020156 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.7293. Min Act: -0.0000

Data Index: 680945 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1290192 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.9332. Min Act: -0.0000

Data Index: 36395 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1159962 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.6068. Min Act: -0.0000

Data Index: 286003 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.6430. Min Range: -2.6430

Max Act: 1.5854. Min Act: -0.0000

Data Index: 157076 (C4 (Web Text))

Max Activating Token Index: 173