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

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

Neuron 3586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2970. Min Range: -2.2970

Max Act: 2.2970. Min Act: -0.0000

Data Index: 1533725 (Python Code)

Max Activating Token Index: 453

Text #1

Max Range: 2.2970. Min Range: -2.2970

Max Act: 2.1199. Min Act: -0.0000

Data Index: 1599401 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 2.2970. Min Range: -2.2970

Max Act: 2.0161. Min Act: -0.0000

Data Index: 1593368 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.8756. Min Act: -0.0000

Data Index: 1603245 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.9677. Min Act: -0.0000

Data Index: 1482083 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.9345. Min Act: -0.0000

Data Index: 1450228 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.9213. Min Act: -0.0000

Data Index: 1474850 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.8240. Min Act: -0.0000

Data Index: 1414749 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.7180. Min Act: -0.0000

Data Index: 1453563 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1433018 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.8458. Min Act: -0.0000

Data Index: 1454693 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1523250 (Python Code)

Max Activating Token Index: 71

Text #12

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1379078 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.6637. Min Act: -0.0000

Data Index: 1615562 (Python Code)

Max Activating Token Index: 726

Text #14

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1382996 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1591981 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.6211. Min Act: -0.0000

Data Index: 1416333 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.7091. Min Act: -0.0000

Data Index: 1484207 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1572964 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 2.2970. Min Range: -2.2970

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1479635 (Python Code)

Max Activating Token Index: 385