Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3620. Min Act: -0.0001

Data Index: 94037 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3330. Min Act: -0.0001

Data Index: 205463 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2991. Min Act: -0.0001

Data Index: 408656 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2903. Min Act: -0.0001

Data Index: 634487 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2423. Min Act: -0.0001

Data Index: 388673 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2259. Min Act: -0.0001

Data Index: 252452 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1313906 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2210. Min Act: -0.0001

Data Index: 58977 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1818. Min Act: -0.0001

Data Index: 807113 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1483. Min Act: -0.0001

Data Index: 787162 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1332. Min Act: -0.0001

Data Index: 594867 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1330. Min Act: -0.0001

Data Index: 363909 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1377. Min Act: -0.0000

Data Index: 553588 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1412. Min Act: -0.0001

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1243. Min Act: -0.0001

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1213. Min Act: -0.0001

Data Index: 755616 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1176399 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1267. Min Act: -0.0001

Data Index: 864396 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1173. Min Act: -0.0001

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 199