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

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

Neuron 966 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1193. Min Range: -4.1193

Max Act: 4.1193. Min Act: -0.0000

Data Index: 1422672 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.9754. Min Act: -0.0000

Data Index: 1380182 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.8921. Min Act: -0.0000

Data Index: 1539287 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.6051. Min Act: -0.0000

Data Index: 1510253 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3212. Min Act: -0.0000

Data Index: 1367138 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.4399. Min Act: -0.0000

Data Index: 1551686 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.4298. Min Act: -0.0000

Data Index: 1617111 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.4298. Min Act: -0.0000

Data Index: 1536057 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3950. Min Act: -0.0000

Data Index: 1551666 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3932. Min Act: -0.0000

Data Index: 1424216 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1515096 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1379218 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.2491. Min Act: -0.0000

Data Index: 1576563 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.1783. Min Act: -0.0000

Data Index: 1598707 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3744. Min Act: -0.0000

Data Index: 1474291 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.2651. Min Act: -0.0000

Data Index: 1385897 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.3167. Min Act: -0.0000

Data Index: 1398701 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.2549. Min Act: -0.0000

Data Index: 1593913 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.2549. Min Act: -0.0000

Data Index: 1494043 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 4.1193. Min Range: -4.1193

Max Act: 2.2342. Min Act: -0.0000

Data Index: 1552917 (Python Code)

Max Activating Token Index: 23