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

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

Neuron 845 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.4439. Min Act: -0.0001

Data Index: 1637733 (Python Code)

Max Activating Token Index: 606

Text #1

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1489502 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3606. Min Act: -0.0001

Data Index: 1561825 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1483780 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3514. Min Act: -0.0001

Data Index: 1395696 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1509087 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3454. Min Act: -0.0001

Data Index: 1639007 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1371634 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1402172 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1549166 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1486402 (Python Code)

Max Activating Token Index: 525

Text #11

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1484971 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1603543 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1404313 (Python Code)

Max Activating Token Index: 729

Text #14

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1597070 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1416140 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1616126 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3071. Min Act: -0.0001

Data Index: 1597560 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.2958. Min Act: -0.0001

Data Index: 1567884 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.2964. Min Act: -0.0001

Data Index: 1407224 (Python Code)

Max Activating Token Index: 325