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

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

Neuron 2376 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: 0.6214. Min Range: -0.6214

Max Act: 0.6214. Min Act: -0.0001

Data Index: 391844 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.6013. Min Act: -0.0001

Data Index: 763687 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5352. Min Act: -0.0001

Data Index: 173546 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5483. Min Act: -0.0001

Data Index: 1110932 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4696. Min Act: -0.0001

Data Index: 1092195 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1116967 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4531. Min Act: -0.0001

Data Index: 519717 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4433. Min Act: -0.0001

Data Index: 1112000 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4500. Min Act: -0.0001

Data Index: 136087 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1110414 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4605. Min Act: -0.0001

Data Index: 701191 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4578. Min Act: -0.0001

Data Index: 993320 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4237. Min Act: -0.0001

Data Index: 338839 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4327. Min Act: -0.0001

Data Index: 366952 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4473. Min Act: -0.0001

Data Index: 768513 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1142938 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4236. Min Act: -0.0001

Data Index: 114579 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1091961 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4031. Min Act: -0.0001

Data Index: 743897 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3858. Min Act: -0.0001

Data Index: 1099526 (C4 (Web Text))

Max Activating Token Index: 832