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

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

Neuron 2457 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.3223. Min Act: -0.0001

Data Index: 3856 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2756. Min Act: -0.0001

Data Index: 480139 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2634. Min Act: -0.0001

Data Index: 1105457 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2597. Min Act: -0.0001

Data Index: 974136 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2533. Min Act: -0.0001

Data Index: 774845 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2483. Min Act: -0.0001

Data Index: 341966 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2333. Min Act: -0.0001

Data Index: 989679 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1234957 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2387. Min Act: -0.0001

Data Index: 1346111 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2345. Min Act: -0.0001

Data Index: 855595 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1257373 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2321. Min Act: -0.0001

Data Index: 626064 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2059. Min Act: -0.0001

Data Index: 920130 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1286246 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2120. Min Act: -0.0001

Data Index: 546037 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2044. Min Act: -0.0001

Data Index: 256977 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2198. Min Act: -0.0001

Data Index: 369079 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2097. Min Act: -0.0001

Data Index: 612972 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1179054 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.3223. Min Range: -0.3223

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1318887 (C4 (Web Text))

Max Activating Token Index: 695