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

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

Neuron 3215 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.4994. Min Act: -0.0001

Data Index: 1641052 (Python Code)

Max Activating Token Index: 247

Text #1

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.5153. Min Act: -0.0001

Data Index: 1569618 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.4414. Min Act: -0.0001

Data Index: 1379078 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3526. Min Act: -0.0001

Data Index: 1372343 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3548. Min Act: -0.0001

Data Index: 1418329 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3383. Min Act: -0.0001

Data Index: 1429547 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3010. Min Act: -0.0001

Data Index: 1416774 (Python Code)

Max Activating Token Index: 525

Text #7

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3167. Min Act: -0.0001

Data Index: 1565255 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3617. Min Act: -0.0001

Data Index: 1517968 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3693. Min Act: -0.0001

Data Index: 1541334 (Python Code)

Max Activating Token Index: 668

Text #10

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3417. Min Act: -0.0001

Data Index: 1489831 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3664. Min Act: -0.0001

Data Index: 1429179 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3463. Min Act: -0.0001

Data Index: 1379457 (Python Code)

Max Activating Token Index: 982

Text #13

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3855. Min Act: -0.0001

Data Index: 1608699 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.2498. Min Act: -0.0001

Data Index: 1597848 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.2804. Min Act: -0.0001

Data Index: 1589112 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.2795. Min Act: -0.0001

Data Index: 1501992 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.3076. Min Act: -0.0001

Data Index: 1620798 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1381610 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 1.5153. Min Range: -1.5153

Max Act: 1.1560. Min Act: -0.0001

Data Index: 1407213 (Python Code)

Max Activating Token Index: 804