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

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

Neuron 1735 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: 1.2985. Min Range: -1.2985

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1051258 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1575160 (Python Code)

Max Activating Token Index: 455

Text #2

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1078103 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1504695 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8525. Min Act: -0.0000

Data Index: 693134 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1562992 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1542524 (Python Code)

Max Activating Token Index: 566

Text #7

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1542565 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1557998 (Python Code)

Max Activating Token Index: 213

Text #9

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1767 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1208491 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1273206 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.6533. Min Act: -0.0000

Data Index: 915851 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1424246 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1191664 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1135115 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.5919. Min Act: -0.0000

Data Index: 651904 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.6267. Min Act: -0.0000

Data Index: 994081 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.5874. Min Act: -0.0000

Data Index: 50615 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.5619. Min Act: -0.0000

Data Index: 129042 (C4 (Web Text))

Max Activating Token Index: 807