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

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

Neuron 2216 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.2764. Min Act: -0.0001

Data Index: 188881 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0729. Min Act: -0.0001

Data Index: 31353 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1352456 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.9974. Min Act: -0.0001

Data Index: 451945 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.9639. Min Act: -0.0001

Data Index: 927021 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.9969. Min Act: -0.0001

Data Index: 702324 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.9140. Min Act: -0.0001

Data Index: 111914 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.7500. Min Act: -0.0001

Data Index: 562718 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8289. Min Act: -0.0001

Data Index: 757589 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8149. Min Act: -0.0001

Data Index: 661479 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1293817 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.7960. Min Act: -0.0001

Data Index: 559322 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8269. Min Act: -0.0001

Data Index: 786838 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8999. Min Act: -0.0001

Data Index: 456885 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8302. Min Act: -0.0001

Data Index: 612366 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.7984. Min Act: -0.0001

Data Index: 910727 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8743. Min Act: -0.0001

Data Index: 1067398 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.8133. Min Act: -0.0001

Data Index: 693288 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.7935. Min Act: -0.0001

Data Index: 903253 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.2764. Min Range: -1.2764

Max Act: 0.9079. Min Act: -0.0001

Data Index: 696524 (C4 (Web Text))

Max Activating Token Index: 95