Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3823 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5450. Min Act: -0.0001

Data Index: 593827 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5343. Min Act: -0.0001

Data Index: 869499 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5344. Min Act: -0.0001

Data Index: 77713 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1550053 (Python Code)

Max Activating Token Index: 898

Text #4

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5376. Min Act: -0.0001

Data Index: 98580 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4963. Min Act: -0.0001

Data Index: 1103980 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5244. Min Act: -0.0001

Data Index: 115327 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5123. Min Act: -0.0001

Data Index: 1298579 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5001. Min Act: -0.0001

Data Index: 209784 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1191662 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1104287 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4827. Min Act: -0.0001

Data Index: 811698 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5128. Min Act: -0.0001

Data Index: 102936 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4985. Min Act: -0.0001

Data Index: 47769 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5130. Min Act: -0.0001

Data Index: 680692 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5099. Min Act: -0.0001

Data Index: 1413814 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4713. Min Act: -0.0001

Data Index: 712380 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4708. Min Act: -0.0001

Data Index: 709887 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4902. Min Act: -0.0001

Data Index: 540427 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5025. Min Act: -0.0001

Data Index: 601741 (C4 (Web Text))

Max Activating Token Index: 995