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

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

Neuron 2749 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: 3.4210. Min Range: -3.4210

Max Act: 3.3160. Min Act: -0.0001

Data Index: 1378396 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2964. Min Act: -0.0001

Data Index: 1587485 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.4210. Min Act: -0.0001

Data Index: 1556563 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3571. Min Act: -0.0001

Data Index: 1444613 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.1761. Min Act: -0.0001

Data Index: 1550454 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2561. Min Act: -0.0001

Data Index: 1479417 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3759. Min Act: -0.0001

Data Index: 1535105 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.0089. Min Act: -0.0001

Data Index: 1400347 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3127. Min Act: -0.0001

Data Index: 1367884 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.1479. Min Act: -0.0001

Data Index: 1527744 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.1301. Min Act: -0.0001

Data Index: 1439253 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 3.4210. Min Range: -3.4210

Max Act: 2.9443. Min Act: -0.0001

Data Index: 1443099 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2029. Min Act: -0.0001

Data Index: 1504965 (Python Code)

Max Activating Token Index: 520

Text #13

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.0351. Min Act: -0.0001

Data Index: 1508628 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.0091. Min Act: -0.0001

Data Index: 1429475 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.0214. Min Act: -0.0001

Data Index: 1405672 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 3.4210. Min Range: -3.4210

Max Act: 2.9804. Min Act: -0.0001

Data Index: 1595011 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 3.4210. Min Range: -3.4210

Max Act: 2.7241. Min Act: -0.0001

Data Index: 1393132 (Python Code)

Max Activating Token Index: 739

Text #18

Max Range: 3.4210. Min Range: -3.4210

Max Act: 2.7780. Min Act: -0.0001

Data Index: 1597545 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 3.4210. Min Range: -3.4210

Max Act: 2.8247. Min Act: -0.0001

Data Index: 1367294 (Python Code)

Max Activating Token Index: 880