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

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

Neuron 4862 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2202. Min Range: -2.2202

Max Act: 2.2202. Min Act: -0.0000

Data Index: 124025 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 2.2202. Min Range: -2.2202

Max Act: 2.1539. Min Act: -0.0000

Data Index: 462463 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.8434. Min Act: -0.0000

Data Index: 998843 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.7106. Min Act: 0.0000

Data Index: 858899 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.8066. Min Act: -0.0000

Data Index: 619073 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.7846. Min Act: 0.0000

Data Index: 640622 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.6509. Min Act: -0.0000

Data Index: 928575 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.6491. Min Act: -0.0000

Data Index: 516497 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.5420. Min Act: -0.0000

Data Index: 947291 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1021531 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.4948. Min Act: -0.0000

Data Index: 1049556 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.4718. Min Act: -0.0000

Data Index: 250199 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1184562 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.4617. Min Act: -0.0000

Data Index: 38194 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.4559. Min Act: -0.0000

Data Index: 432300 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.4222. Min Act: -0.0000

Data Index: 656736 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.3932. Min Act: -0.0000

Data Index: 801126 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.3783. Min Act: -0.0000

Data Index: 69110 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.2949. Min Act: -0.0000

Data Index: 833728 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.2202. Min Range: -2.2202

Max Act: 1.3223. Min Act: -0.0000

Data Index: 510035 (C4 (Web Text))

Max Activating Token Index: 812