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

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

Neuron 2599 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1159. Min Range: -1.1159

Max Act: 1.1159. Min Act: -0.0000

Data Index: 38164 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.9355. Min Act: -0.0000

Data Index: 488485 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8937. Min Act: -0.0000

Data Index: 167584 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.9008. Min Act: -0.0000

Data Index: 721114 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8582. Min Act: -0.0000

Data Index: 307609 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8472. Min Act: -0.0000

Data Index: 91801 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8441. Min Act: -0.0000

Data Index: 905203 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8287. Min Act: -0.0000

Data Index: 967155 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1185819 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1134912 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7880. Min Act: -0.0000

Data Index: 805992 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7836. Min Act: -0.0000

Data Index: 578916 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7778. Min Act: -0.0000

Data Index: 404068 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.8195. Min Act: -0.0000

Data Index: 895131 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7523. Min Act: -0.0000

Data Index: 911185 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1170266 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7085. Min Act: -0.0000

Data Index: 466224 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1115899 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.7014. Min Act: -0.0000

Data Index: 359321 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.1159. Min Range: -1.1159

Max Act: 0.6886. Min Act: -0.0000

Data Index: 731570 (C4 (Web Text))

Max Activating Token Index: 730