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

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

Neuron 1854 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: 0.8943. Min Range: -0.8943

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1436234 (Python Code)

Max Activating Token Index: 894

Text #1

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1422322 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1483136 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1395363 (Python Code)

Max Activating Token Index: 989

Text #4

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6996. Min Act: -0.0001

Data Index: 1528141 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1467383 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1518125 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1438953 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1504110 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1458890 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6818. Min Act: -0.0001

Data Index: 1447826 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1604512 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6865. Min Act: -0.0001

Data Index: 1415761 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1392089 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1388927 (Python Code)

Max Activating Token Index: 623

Text #15

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1543660 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1362455 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1377627 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1374328 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.8943. Min Range: -0.8943

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1363949 (Python Code)

Max Activating Token Index: 163