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

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

Neuron 2765 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: 6.6407. Min Range: -6.6407

Max Act: 6.5470. Min Act: 0.0000

Data Index: 975093 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 6.6407. Min Range: -6.6407

Max Act: 6.6407. Min Act: -0.0000

Data Index: 906244 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 6.6407. Min Range: -6.6407

Max Act: 6.2649. Min Act: -0.0000

Data Index: 1188347 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.4913. Min Act: -0.0000

Data Index: 425205 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.8068. Min Act: -0.0000

Data Index: 781676 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.1196. Min Act: 0.0000

Data Index: 699408 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.1015. Min Act: -0.0000

Data Index: 373889 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.8516. Min Act: -0.0000

Data Index: 1039645 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.0769. Min Act: -0.0000

Data Index: 803661 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.9320. Min Act: 0.0000

Data Index: 1323594 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.9212. Min Act: -0.0000

Data Index: 933111 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.0755. Min Act: -0.0000

Data Index: 174374 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.7944. Min Act: 0.0000

Data Index: 1308710 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 6.6407. Min Range: -6.6407

Max Act: 5.1544. Min Act: 0.0000

Data Index: 1006966 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.7399. Min Act: 0.0000

Data Index: 640859 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.6907. Min Act: -0.0000

Data Index: 504676 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.6808. Min Act: 0.0000

Data Index: 155057 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.6460. Min Act: 0.0000

Data Index: 1119842 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.6343. Min Act: -0.0000

Data Index: 525573 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 6.6407. Min Range: -6.6407

Max Act: 4.6241. Min Act: -0.0000

Data Index: 765530 (C4 (Web Text))

Max Activating Token Index: 13