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

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

Neuron 843 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2948. Min Act: -0.0001

Data Index: 1552223 (Python Code)

Max Activating Token Index: 310

Text #1

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2815. Min Act: -0.0001

Data Index: 1526618 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2984. Min Act: -0.0001

Data Index: 1373816 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2910. Min Act: -0.0001

Data Index: 1460001 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2049. Min Act: -0.0001

Data Index: 1448948 (Python Code)

Max Activating Token Index: 530

Text #5

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2273. Min Act: -0.0001

Data Index: 1390051 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1943. Min Act: -0.0001

Data Index: 1438179 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1877. Min Act: -0.0001

Data Index: 1367497 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2875. Min Act: -0.0001

Data Index: 1430236 (Python Code)

Max Activating Token Index: 67

Text #9

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2227. Min Act: -0.0001

Data Index: 1554499 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2197. Min Act: -0.0001

Data Index: 1626330 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2156. Min Act: -0.0001

Data Index: 1376119 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2097. Min Act: -0.0001

Data Index: 1445067 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2105. Min Act: -0.0001

Data Index: 1492451 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1929. Min Act: -0.0001

Data Index: 1429798 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1243. Min Act: -0.0001

Data Index: 1455676 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2318. Min Act: -0.0001

Data Index: 1639836 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1433109 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1901. Min Act: -0.0001

Data Index: 1422601 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1793. Min Act: -0.0001

Data Index: 1648589 (Python Code)

Max Activating Token Index: 34