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

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

Neuron 238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1384871 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.3788. Min Act: -0.0000

Data Index: 1392536 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4014. Min Act: -0.0000

Data Index: 84974 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.4420. Min Act: -0.0000

Data Index: 155532 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.1952. Min Act: -0.0000

Data Index: 32437 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1572171 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0560. Min Act: -0.0000

Data Index: 684759 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1505903 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1546529 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1204369 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1394266 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1622093 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1527057 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1594487 (Python Code)

Max Activating Token Index: 288

Text #14

Max Range: 1.4420. Min Range: -1.4420

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1421470 (Python Code)

Max Activating Token Index: 945

Text #15

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1593054 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.9769. Min Act: -0.0001

Data Index: 1556367 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.8938. Min Act: -0.0000

Data Index: 430049 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1653693 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 1.4420. Min Range: -1.4420

Max Act: 0.8470. Min Act: -0.0000

Data Index: 995436 (C4 (Web Text))

Max Activating Token Index: 540