Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4129 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0396. Min Act: -0.0001

Data Index: 703207 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0001

Data Index: 260149 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1251289 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0356. Min Act: -0.0001

Data Index: 417294 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0347. Min Act: -0.0001

Data Index: 832763 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1116632 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0388. Min Act: -0.0001

Data Index: 363602 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0346. Min Act: -0.0001

Data Index: 155824 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0357. Min Act: -0.0001

Data Index: 22204 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0327. Min Act: -0.0001

Data Index: 906901 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0340. Min Act: -0.0001

Data Index: 750211 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0302. Min Act: -0.0001

Data Index: 332145 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0310. Min Act: -0.0001

Data Index: 688965 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0296. Min Act: -0.0001

Data Index: 315488 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0288. Min Act: -0.0001

Data Index: 813717 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0308. Min Act: -0.0001

Data Index: 45555 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0276. Min Act: -0.0001

Data Index: 298811 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1228634 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0297. Min Act: -0.0001

Data Index: 268019 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0280. Min Act: -0.0001

Data Index: 793323 (C4 (Web Text))

Max Activating Token Index: 949