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

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

Neuron 3620 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.2611. Min Act: -0.0000

Data Index: 1615790 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1611519 (Python Code)

Max Activating Token Index: 318

Text #2

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1653363 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1451835 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1428816 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1534170 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1376351 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 1.2611. Min Range: -1.2611

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1453876 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9799. Min Act: -0.0001

Data Index: 1467997 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.8303. Min Act: -0.0001

Data Index: 1461978 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9362. Min Act: -0.0001

Data Index: 1504863 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1463040 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1483376 (Python Code)

Max Activating Token Index: 259

Text #13

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1545087 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1612321 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1615994 (Python Code)

Max Activating Token Index: 966

Text #16

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1485249 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1436970 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1447554 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 1.2611. Min Range: -1.2611

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1519574 (Python Code)

Max Activating Token Index: 410