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

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

Neuron 6057 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.3272. Min Act: -0.0000

Data Index: 1628616 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.8489. Min Act: -0.0000

Data Index: 1614238 (Python Code)

Max Activating Token Index: 427

Text #2

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.2150. Min Act: -0.0000

Data Index: 1623917 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.1851. Min Act: -0.0000

Data Index: 1373107 (Python Code)

Max Activating Token Index: 853

Text #4

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.0330. Min Act: -0.0000

Data Index: 1381792 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.0100. Min Act: -0.0000

Data Index: 1455541 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 6.8489. Min Range: -6.8489

Max Act: 6.1788. Min Act: -0.0000

Data Index: 1444741 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.6420. Min Act: -0.0000

Data Index: 1413676 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.8237. Min Act: -0.0000

Data Index: 1469903 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.6487. Min Act: -0.0000

Data Index: 1514517 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.7209. Min Act: -0.0000

Data Index: 1455091 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.3171. Min Act: -0.0000

Data Index: 1591509 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.7001. Min Act: -0.0000

Data Index: 1585639 (Python Code)

Max Activating Token Index: 562

Text #13

Max Range: 6.8489. Min Range: -6.8489

Max Act: 4.4909. Min Act: -0.0000

Data Index: 1621273 (Python Code)

Max Activating Token Index: 373

Text #14

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.2269. Min Act: -0.0000

Data Index: 1557870 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.3797. Min Act: -0.0000

Data Index: 1485811 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.3927. Min Act: -0.0000

Data Index: 1496909 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 6.8489. Min Range: -6.8489

Max Act: 5.3363. Min Act: -0.0000

Data Index: 1650630 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 6.8489. Min Range: -6.8489

Max Act: 4.9288. Min Act: -0.0000

Data Index: 1620805 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 6.8489. Min Range: -6.8489

Max Act: 4.9278. Min Act: -0.0000

Data Index: 1605181 (Python Code)

Max Activating Token Index: 627