Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1413 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6154. Min Act: -0.0002

Data Index: 1594117 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0002

Data Index: 1363352 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5787. Min Act: -0.0002

Data Index: 1504038 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5388. Min Act: -0.0002

Data Index: 1585030 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5536. Min Act: -0.0002

Data Index: 1595766 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5429. Min Act: -0.0002

Data Index: 1489125 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5330. Min Act: -0.0002

Data Index: 1587360 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5390. Min Act: -0.0002

Data Index: 1533479 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5232. Min Act: -0.0002

Data Index: 1476262 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5223. Min Act: -0.0002

Data Index: 1567791 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5165. Min Act: -0.0002

Data Index: 1510954 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5282. Min Act: -0.0002

Data Index: 1612659 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5198. Min Act: -0.0002

Data Index: 1419054 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5120. Min Act: -0.0002

Data Index: 1473446 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5197. Min Act: -0.0002

Data Index: 1528214 (Python Code)

Max Activating Token Index: 670

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5095. Min Act: -0.0002

Data Index: 1395676 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4990. Min Act: -0.0002

Data Index: 1652838 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4881. Min Act: -0.0002

Data Index: 1504557 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4989. Min Act: -0.0002

Data Index: 1529235 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4925. Min Act: -0.0002

Data Index: 1632402 (Python Code)

Max Activating Token Index: 15