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

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

Neuron 3766 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: 1.4852. Min Range: -1.4852

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1595085 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1634464 (Python Code)

Max Activating Token Index: 218

Text #2

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4852. Min Act: -0.0000

Data Index: 82270 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2626. Min Act: -0.0000

Data Index: 665355 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2657. Min Act: -0.0000

Data Index: 86220 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4069. Min Act: -0.0000

Data Index: 754917 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.3112. Min Act: -0.0000

Data Index: 807407 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1368991 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1513850 (Python Code)

Max Activating Token Index: 913

Text #9

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1615743 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2596. Min Act: -0.0000

Data Index: 582899 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1623950 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1907. Min Act: -0.0000

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1233023 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1365186 (Python Code)

Max Activating Token Index: 831

Text #15

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1543. Min Act: -0.0000

Data Index: 995758 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1956. Min Act: -0.0000

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1636003 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1484453 (Python Code)

Max Activating Token Index: 525

Text #19

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1410. Min Act: -0.0000

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 837