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

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

Neuron 6094 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.4659. Min Act: -0.0000

Data Index: 1255745 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.5712. Min Act: -0.0000

Data Index: 469024 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.3134. Min Act: -0.0000

Data Index: 724804 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.3964. Min Act: -0.0000

Data Index: 318409 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.3824. Min Act: -0.0000

Data Index: 496533 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.2219. Min Act: -0.0000

Data Index: 1622522 (Python Code)

Max Activating Token Index: 876

Text #6

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.1081. Min Act: -0.0000

Data Index: 1643638 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.2105. Min Act: -0.0000

Data Index: 727954 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.0926. Min Act: -0.0000

Data Index: 115990 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.2070. Min Act: -0.0000

Data Index: 500264 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.1164. Min Act: -0.0000

Data Index: 1402409 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.0715. Min Act: -0.0000

Data Index: 1335776 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.0700. Min Act: -0.0000

Data Index: 768951 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.0379. Min Act: -0.0000

Data Index: 1117730 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 2.5712. Min Range: -2.5712

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1537465 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 2.5712. Min Range: -2.5712

Max Act: 1.9876. Min Act: -0.0000

Data Index: 363505 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 2.5712. Min Range: -2.5712

Max Act: 1.9900. Min Act: -0.0000

Data Index: 41835 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 2.5712. Min Range: -2.5712

Max Act: 1.9743. Min Act: -0.0000

Data Index: 943159 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.5712. Min Range: -2.5712

Max Act: 1.9629. Min Act: -0.0000

Data Index: 508707 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 2.5712. Min Range: -2.5712

Max Act: 2.0691. Min Act: -0.0000

Data Index: 647297 (C4 (Web Text))

Max Activating Token Index: 973