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

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

Neuron 3247 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7952. Min Range: -7.7952

Max Act: 7.7952. Min Act: -0.0001

Data Index: 1635966 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 7.7952. Min Range: -7.7952

Max Act: 7.5073. Min Act: -0.0001

Data Index: 1439782 (Python Code)

Max Activating Token Index: 962

Text #2

Max Range: 7.7952. Min Range: -7.7952

Max Act: 6.5792. Min Act: -0.0001

Data Index: 1572593 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 7.7952. Min Range: -7.7952

Max Act: 7.1123. Min Act: -0.0001

Data Index: 1390957 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 7.7952. Min Range: -7.7952

Max Act: 6.4255. Min Act: -0.0001

Data Index: 1528674 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.7710. Min Act: -0.0001

Data Index: 1556026 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.2486. Min Act: -0.0001

Data Index: 1378975 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.4675. Min Act: -0.0001

Data Index: 1399855 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.9409. Min Act: -0.0001

Data Index: 1610751 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.6396. Min Act: -0.0001

Data Index: 1643851 (Python Code)

Max Activating Token Index: 315

Text #10

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.0182. Min Act: -0.0001

Data Index: 1397778 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.8913. Min Act: -0.0001

Data Index: 1443484 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.8173. Min Act: -0.0001

Data Index: 1614632 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.8160. Min Act: -0.0001

Data Index: 1593453 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.5251. Min Act: -0.0001

Data Index: 1467006 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.5320. Min Act: -0.0001

Data Index: 1451605 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 7.7952. Min Range: -7.7952

Max Act: 5.2279. Min Act: -0.0001

Data Index: 1398819 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.6866. Min Act: -0.0001

Data Index: 1361580 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.7938. Min Act: -0.0001

Data Index: 1595465 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 7.7952. Min Range: -7.7952

Max Act: 4.3788. Min Act: -0.0001

Data Index: 1415732 (Python Code)

Max Activating Token Index: 183