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

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

Neuron 2170 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.3263. Min Act: -0.0001

Data Index: 1285704 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2117. Min Act: -0.0001

Data Index: 854669 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.2802. Min Act: -0.0001

Data Index: 94678 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1459. Min Act: -0.0001

Data Index: 955981 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1867. Min Act: -0.0001

Data Index: 1316202 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1191. Min Act: -0.0001

Data Index: 891100 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.1876. Min Act: -0.0001

Data Index: 855644 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0413. Min Act: -0.0001

Data Index: 742500 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0441. Min Act: -0.0001

Data Index: 683578 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0916. Min Act: -0.0001

Data Index: 237967 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 1.3263. Min Range: -1.3263

Max Act: 1.0401. Min Act: -0.0001

Data Index: 1288917 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.8896. Min Act: -0.0001

Data Index: 687917 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.9588. Min Act: -0.0001

Data Index: 557993 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.8863. Min Act: -0.0001

Data Index: 257092 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1207911 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.9037. Min Act: -0.0001

Data Index: 961057 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.8818. Min Act: -0.0001

Data Index: 787129 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.8549. Min Act: -0.0001

Data Index: 575683 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.9057. Min Act: -0.0001

Data Index: 228158 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.3263. Min Range: -1.3263

Max Act: 0.8374. Min Act: -0.0001

Data Index: 278775 (C4 (Web Text))

Max Activating Token Index: 106