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

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

Neuron 3020 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.8660. Min Act: -0.0000

Data Index: 1330367 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 4.0593. Min Range: -4.0593

Max Act: 4.0593. Min Act: -0.0000

Data Index: 1088515 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.8840. Min Act: -0.0000

Data Index: 974004 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.6914. Min Act: -0.0000

Data Index: 1206277 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.6994. Min Act: -0.0000

Data Index: 725767 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.8521. Min Act: -0.0000

Data Index: 454333 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.5048. Min Act: -0.0000

Data Index: 255177 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.7713. Min Act: -0.0000

Data Index: 1151195 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.0697. Min Act: -0.0000

Data Index: 1156400 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.6547. Min Act: -0.0000

Data Index: 963837 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.3450. Min Act: -0.0000

Data Index: 1189833 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.4770. Min Act: -0.0000

Data Index: 965516 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.4252. Min Act: -0.0000

Data Index: 887535 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.2789. Min Act: -0.0000

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.2511. Min Act: -0.0000

Data Index: 1161177 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.0704. Min Act: -0.0000

Data Index: 1342161 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.2063. Min Act: -0.0000

Data Index: 811012 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.3522. Min Act: -0.0000

Data Index: 718913 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.5022. Min Act: -0.0000

Data Index: 168700 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 4.0593. Min Range: -4.0593

Max Act: 3.3088. Min Act: -0.0000

Data Index: 1190300 (C4 (Web Text))

Max Activating Token Index: 152