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

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

Neuron 5891 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: 2.3408. Min Range: -2.3408

Max Act: 2.3408. Min Act: -0.0000

Data Index: 253626 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 2.3408. Min Range: -2.3408

Max Act: 2.1560. Min Act: -0.0000

Data Index: 67250 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.8924. Min Act: -0.0000

Data Index: 805926 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.9976. Min Act: -0.0000

Data Index: 656433 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1470318 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.6126. Min Act: -0.0000

Data Index: 38890 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1180277 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.5024. Min Act: -0.0000

Data Index: 704880 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.5953. Min Act: -0.0000

Data Index: 905638 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.5097. Min Act: -0.0000

Data Index: 616378 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.4129. Min Act: -0.0000

Data Index: 972825 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1232133 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.4231. Min Act: -0.0000

Data Index: 774383 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.4140. Min Act: -0.0000

Data Index: 77766 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.4337. Min Act: -0.0000

Data Index: 517630 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.4089. Min Act: -0.0000

Data Index: 639424 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.4003. Min Act: -0.0000

Data Index: 456718 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.3100. Min Act: -0.0000

Data Index: 560991 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.3508. Min Act: -0.0000

Data Index: 362357 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 2.3408. Min Range: -2.3408

Max Act: 1.3668. Min Act: -0.0000

Data Index: 236178 (C4 (Web Text))

Max Activating Token Index: 744