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

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

Neuron 3782 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.4102. Min Act: -0.0002

Data Index: 811834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.4021. Min Act: -0.0002

Data Index: 1335122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3959. Min Act: -0.0002

Data Index: 567708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3956. Min Act: -0.0002

Data Index: 1283781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3599. Min Act: -0.0002

Data Index: 1070827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3558. Min Act: -0.0002

Data Index: 1056866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3535. Min Act: -0.0002

Data Index: 1297355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3532. Min Act: -0.0002

Data Index: 1286234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3644. Min Act: -0.0002

Data Index: 110092 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3469. Min Act: -0.0002

Data Index: 132129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3458. Min Act: -0.0002

Data Index: 676757 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3461. Min Act: -0.0002

Data Index: 642883 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3455. Min Act: -0.0002

Data Index: 505296 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3448. Min Act: -0.0002

Data Index: 104780 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3399. Min Act: -0.0002

Data Index: 1316527 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3398. Min Act: -0.0002

Data Index: 1233747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3395. Min Act: -0.0002

Data Index: 893730 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3356. Min Act: -0.0002

Data Index: 128164 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3341. Min Act: -0.0002

Data Index: 127782 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3313. Min Act: -0.0002

Data Index: 244528 (C4 (Web Text))

Max Activating Token Index: 1023