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

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

Neuron 3551 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1177319 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9934. Min Act: -0.0000

Data Index: 188956 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1119751 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9263. Min Act: -0.0000

Data Index: 520978 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7942. Min Act: -0.0000

Data Index: 818978 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.8098. Min Act: -0.0000

Data Index: 129537 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.8012. Min Act: -0.0000

Data Index: 301765 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1026733 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6949. Min Act: -0.0000

Data Index: 554172 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7914. Min Act: -0.0000

Data Index: 383079 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7599. Min Act: -0.0000

Data Index: 961946 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1227505 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1189062 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7151. Min Act: -0.0000

Data Index: 990071 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6961. Min Act: -0.0000

Data Index: 468500 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7283. Min Act: -0.0000

Data Index: 614166 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7016. Min Act: -0.0000

Data Index: 309597 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1344330 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6952. Min Act: -0.0000

Data Index: 634731 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6891. Min Act: -0.0000

Data Index: 312242 (C4 (Web Text))

Max Activating Token Index: 443