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

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

Neuron 927 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.7517. Min Act: -0.0001

Data Index: 655115 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5116. Min Act: -0.0001

Data Index: 681119 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5493. Min Act: -0.0001

Data Index: 1266574 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4688. Min Act: -0.0001

Data Index: 1245169 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4146. Min Act: -0.0001

Data Index: 488661 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5508. Min Act: -0.0001

Data Index: 821656 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4641. Min Act: -0.0001

Data Index: 275951 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4970. Min Act: -0.0001

Data Index: 1164952 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5424. Min Act: -0.0001

Data Index: 130379 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4446. Min Act: -0.0001

Data Index: 945087 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4805. Min Act: -0.0001

Data Index: 378431 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4281. Min Act: -0.0001

Data Index: 257867 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5186. Min Act: -0.0001

Data Index: 98897 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4535. Min Act: -0.0001

Data Index: 991828 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5110. Min Act: -0.0001

Data Index: 1348 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4073. Min Act: -0.0001

Data Index: 1264336 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4241. Min Act: -0.0001

Data Index: 271102 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.3963. Min Act: -0.0001

Data Index: 548604 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4409. Min Act: -0.0001

Data Index: 631494 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4004. Min Act: -0.0001

Data Index: 391988 (C4 (Web Text))

Max Activating Token Index: 550