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

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

Neuron 1855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2845. Min Act: -0.0002

Data Index: 733028 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2866. Min Act: -0.0002

Data Index: 534422 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2870. Min Act: -0.0002

Data Index: 544747 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2644. Min Act: -0.0002

Data Index: 350644 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2681. Min Act: -0.0002

Data Index: 578650 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2563. Min Act: -0.0002

Data Index: 531634 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2543. Min Act: -0.0002

Data Index: 301288 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2524. Min Act: -0.0002

Data Index: 83264 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2612. Min Act: -0.0002

Data Index: 621383 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2612. Min Act: -0.0002

Data Index: 425797 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2504. Min Act: -0.0002

Data Index: 601503 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2383. Min Act: -0.0002

Data Index: 944357 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2488. Min Act: -0.0002

Data Index: 514742 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2450. Min Act: -0.0002

Data Index: 1078679 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2439. Min Act: -0.0002

Data Index: 1105887 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2671. Min Act: -0.0002

Data Index: 179354 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2365. Min Act: -0.0002

Data Index: 98657 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2364. Min Act: -0.0002

Data Index: 1265252 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2344. Min Act: -0.0002

Data Index: 149813 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2485. Min Act: -0.0002

Data Index: 532567 (C4 (Web Text))

Max Activating Token Index: 264