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

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

Neuron 1846 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: 0.4248. Min Range: -0.4248

Max Act: 0.4248. Min Act: -0.0001

Data Index: 1544576 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1519030 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1412211 (Python Code)

Max Activating Token Index: 687

Text #3

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1395952 (Python Code)

Max Activating Token Index: 319

Text #4

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1546002 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1360528 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1568053 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3516. Min Act: -0.0000

Data Index: 707736 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1656118 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3119. Min Act: -0.0001

Data Index: 188304 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3287. Min Act: -0.0001

Data Index: 1560667 (Python Code)

Max Activating Token Index: 896

Text #11

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3055. Min Act: -0.0001

Data Index: 571829 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1519286 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1571716 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1392850 (Python Code)

Max Activating Token Index: 465

Text #15

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1519031 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1082337 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1513000 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1615641 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 0.4248. Min Range: -0.4248

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1081827 (C4 (Web Text))

Max Activating Token Index: 337