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

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

Neuron 5071 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.6182. Min Act: -0.0000

Data Index: 810534 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.3465. Min Act: -0.0000

Data Index: 630037 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.3157. Min Act: -0.0000

Data Index: 766330 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2528. Min Act: -0.0000

Data Index: 354053 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.3160. Min Act: -0.0000

Data Index: 1241687 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1300210 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2489. Min Act: -0.0000

Data Index: 418837 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.1303. Min Act: -0.0000

Data Index: 895568 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.1140. Min Act: -0.0000

Data Index: 1230935 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2224. Min Act: -0.0000

Data Index: 1065672 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2327. Min Act: -0.0000

Data Index: 13571 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2078. Min Act: -0.0000

Data Index: 637766 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.0451. Min Act: -0.0000

Data Index: 222297 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.1589. Min Act: -0.0000

Data Index: 60578 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.1339. Min Act: -0.0000

Data Index: 114440 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2468. Min Act: -0.0000

Data Index: 434787 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.9630. Min Act: -0.0000

Data Index: 442381 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.0300. Min Act: -0.0000

Data Index: 1163945 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.0290. Min Act: -0.0000

Data Index: 798326 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.0086. Min Act: -0.0000

Data Index: 19023 (C4 (Web Text))

Max Activating Token Index: 418