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

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

Neuron 5570 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.8103. Min Act: -0.0000

Data Index: 543683 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.8050. Min Act: -0.0000

Data Index: 243590 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7713. Min Act: -0.0000

Data Index: 467620 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7212. Min Act: -0.0000

Data Index: 985997 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1640093 (Python Code)

Max Activating Token Index: 584

Text #5

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6712. Min Act: -0.0000

Data Index: 275765 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7105. Min Act: -0.0000

Data Index: 830686 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7092. Min Act: -0.0000

Data Index: 430653 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1224182 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.7076. Min Act: -0.0000

Data Index: 167776 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6900. Min Act: -0.0000

Data Index: 316148 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1308803 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.5626. Min Act: -0.0000

Data Index: 833600 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6508. Min Act: -0.0000

Data Index: 729054 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1400167 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.5590. Min Act: -0.0000

Data Index: 58702 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1286967 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.5831. Min Act: -0.0000

Data Index: 531897 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6164. Min Act: -0.0000

Data Index: 657866 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.8103. Min Range: -0.8103

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1090310 (C4 (Web Text))

Max Activating Token Index: 848