Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1366 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.6264. Min Act: -0.0001

Data Index: 797084 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.5236. Min Act: -0.0001

Data Index: 217665 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.5316. Min Act: -0.0001

Data Index: 1341410 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.5184. Min Act: -0.0001

Data Index: 1353420 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.5144. Min Act: -0.0001

Data Index: 1030165 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.5143. Min Act: -0.0001

Data Index: 1027940 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4866. Min Act: -0.0001

Data Index: 1305422 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.5203. Min Act: -0.0001

Data Index: 841401 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4851. Min Act: -0.0001

Data Index: 129823 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4682. Min Act: -0.0001

Data Index: 1052840 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4775. Min Act: 0.0001

Data Index: 1056450 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4887. Min Act: -0.0001

Data Index: 949441 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4549. Min Act: -0.0001

Data Index: 369749 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4700. Min Act: -0.0001

Data Index: 1144979 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4438. Min Act: -0.0001

Data Index: 706335 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4555. Min Act: -0.0001

Data Index: 98362 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4536. Min Act: -0.0001

Data Index: 1009814 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4711. Min Act: -0.0001

Data Index: 873931 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4567. Min Act: -0.0001

Data Index: 526249 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.6264. Min Range: -0.6264

Max Act: 0.4501. Min Act: -0.0001

Data Index: 1336730 (C4 (Web Text))

Max Activating Token Index: 879