Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4013 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 334414 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8096. Min Act: -0.0000

Data Index: 51710 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1170800 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8102. Min Act: -0.0000

Data Index: 254025 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7253. Min Act: 0.0000

Data Index: 1004459 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7342. Min Act: -0.0000

Data Index: 758735 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1217747 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1182651 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6963. Min Act: -0.0000

Data Index: 53643 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6884. Min Act: -0.0000

Data Index: 228215 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6175. Min Act: -0.0000

Data Index: 734924 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6410. Min Act: -0.0000

Data Index: 617891 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6269. Min Act: -0.0000

Data Index: 887260 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6185. Min Act: -0.0000

Data Index: 159185 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6303. Min Act: -0.0000

Data Index: 266462 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6511. Min Act: -0.0000

Data Index: 349784 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6732. Min Act: -0.0000

Data Index: 278057 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1015860 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1220311 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.5952. Min Act: -0.0000

Data Index: 415940 (C4 (Web Text))

Max Activating Token Index: 1005