Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 792 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.8819. Min Act: -0.0001

Data Index: 327341 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.9060. Min Act: -0.0001

Data Index: 1221343 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.7124. Min Act: -0.0001

Data Index: 1358746 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.2104. Min Act: -0.0001

Data Index: 1052602 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.3787. Min Act: -0.0000

Data Index: 1258549 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.1936. Min Act: -0.0001

Data Index: 1085365 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.1777. Min Act: -0.0001

Data Index: 619684 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.0770. Min Act: -0.0001

Data Index: 956640 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.0770. Min Act: -0.0000

Data Index: 85013 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.0667. Min Act: -0.0001

Data Index: 57288 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.9913. Min Act: -0.0001

Data Index: 445328 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.9008. Min Act: -0.0000

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 2.9060. Min Range: -2.9060

Max Act: 2.0399. Min Act: -0.0001

Data Index: 64957 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.9365. Min Act: -0.0001

Data Index: 672311 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.8696. Min Act: -0.0000

Data Index: 366685 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.6559. Min Act: -0.0000

Data Index: 683393 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.7963. Min Act: -0.0000

Data Index: 1257945 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1244101 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.6787. Min Act: -0.0001

Data Index: 797051 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 2.9060. Min Range: -2.9060

Max Act: 1.8667. Min Act: -0.0001

Data Index: 807898 (C4 (Web Text))

Max Activating Token Index: 881