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

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

Neuron 4468 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: 5.3224. Min Range: -5.3224

Max Act: 5.3224. Min Act: -0.0000

Data Index: 667110 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 5.3224. Min Range: -5.3224

Max Act: 5.0154. Min Act: -0.0000

Data Index: 191243 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.8209. Min Act: -0.0000

Data Index: 644604 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.4018. Min Act: -0.0000

Data Index: 1278440 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.3046. Min Act: -0.0000

Data Index: 3828 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.1903. Min Act: -0.0000

Data Index: 1140555 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.1611. Min Act: -0.0000

Data Index: 353041 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.4481. Min Act: -0.0000

Data Index: 1251405 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.5730. Min Act: -0.0000

Data Index: 583723 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.1395. Min Act: -0.0000

Data Index: 631587 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.0951. Min Act: -0.0000

Data Index: 1054275 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.2318. Min Act: -0.0000

Data Index: 663907 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 5.3224. Min Range: -5.3224

Max Act: 3.6707. Min Act: -0.0000

Data Index: 1124644 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.1070. Min Act: -0.0000

Data Index: 238572 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 5.3224. Min Range: -5.3224

Max Act: 3.7671. Min Act: -0.0000

Data Index: 797216 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 5.3224. Min Range: -5.3224

Max Act: 3.9527. Min Act: -0.0000

Data Index: 43918 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 5.3224. Min Range: -5.3224

Max Act: 4.0932. Min Act: -0.0000

Data Index: 960310 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 5.3224. Min Range: -5.3224

Max Act: 3.7773. Min Act: -0.0000

Data Index: 174972 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 5.3224. Min Range: -5.3224

Max Act: 3.7786. Min Act: -0.0000

Data Index: 89285 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 5.3224. Min Range: -5.3224

Max Act: 3.7588. Min Act: -0.0000

Data Index: 311454 (C4 (Web Text))

Max Activating Token Index: 749