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

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

Neuron 870 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: 0.1396. Min Range: -0.1396

Max Act: 0.1280. Min Act: -0.0001

Data Index: 50875 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1396. Min Act: -0.0001

Data Index: 869733 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1323. Min Act: -0.0001

Data Index: 151929 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1323. Min Act: -0.0001

Data Index: 724764 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1270. Min Act: -0.0001

Data Index: 730293 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1284. Min Act: -0.0001

Data Index: 514701 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1248556 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1210. Min Act: -0.0001

Data Index: 897597 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1017244 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1236. Min Act: -0.0001

Data Index: 559045 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1115640 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1203. Min Act: -0.0001

Data Index: 560680 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1232. Min Act: -0.0001

Data Index: 743218 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1278. Min Act: -0.0001

Data Index: 812037 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1232. Min Act: -0.0001

Data Index: 144471 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1283. Min Act: -0.0001

Data Index: 42495 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1283. Min Act: -0.0001

Data Index: 494910 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1224. Min Act: -0.0001

Data Index: 818688 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1244. Min Act: -0.0001

Data Index: 337787 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1099864 (C4 (Web Text))

Max Activating Token Index: 106