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

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

Neuron 871 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9259. Min Act: -0.0001

Data Index: 487752 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9180. Min Act: -0.0001

Data Index: 773890 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.0063. Min Range: -1.0063

Max Act: 1.0063. Min Act: -0.0001

Data Index: 624940 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8782. Min Act: -0.0001

Data Index: 419722 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9196. Min Act: -0.0001

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.7847. Min Act: -0.0001

Data Index: 1260396 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8603. Min Act: -0.0001

Data Index: 295984 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8814. Min Act: -0.0001

Data Index: 35445 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8855. Min Act: -0.0001

Data Index: 213148 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9028. Min Act: -0.0001

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8474. Min Act: -0.0001

Data Index: 1185493 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8529. Min Act: -0.0001

Data Index: 987272 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8710. Min Act: -0.0001

Data Index: 256937 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8686. Min Act: -0.0001

Data Index: 887042 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8340. Min Act: -0.0001

Data Index: 968168 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8889. Min Act: -0.0001

Data Index: 980586 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8535. Min Act: -0.0001

Data Index: 538365 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.7750. Min Act: -0.0001

Data Index: 1194629 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8220. Min Act: -0.0001

Data Index: 425121 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1149833 (C4 (Web Text))

Max Activating Token Index: 597