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

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

Neuron 4450 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4864. Min Range: -3.4864

Max Act: 3.4864. Min Act: -0.0000

Data Index: 1005352 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 3.4864. Min Range: -3.4864

Max Act: 2.6483. Min Act: -0.0000

Data Index: 809340 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 3.4864. Min Range: -3.4864

Max Act: 2.5588. Min Act: -0.0000

Data Index: 896130 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.4864. Min Range: -3.4864

Max Act: 2.4442. Min Act: -0.0000

Data Index: 325847 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 3.4864. Min Range: -3.4864

Max Act: 2.0105. Min Act: 0.0000

Data Index: 293937 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.9361. Min Act: -0.0000

Data Index: 58119 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 3.4864. Min Range: -3.4864

Max Act: 2.0753. Min Act: -0.0000

Data Index: 379241 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.8170. Min Act: -0.0000

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1297821 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1333248 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.5546. Min Act: -0.0000

Data Index: 50118 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1011751 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.5516. Min Act: 0.0000

Data Index: 959521 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.4367. Min Act: 0.0000

Data Index: 1205099 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1140829 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1026933 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1315467 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.3910. Min Act: -0.0000

Data Index: 55197 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.3481. Min Act: -0.0000

Data Index: 306668 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 3.4864. Min Range: -3.4864

Max Act: 1.3043. Min Act: -0.0000

Data Index: 319189 (C4 (Web Text))

Max Activating Token Index: 590