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

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

Neuron 3568 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: 1.0053. Min Range: -1.0053

Max Act: 0.9686. Min Act: -0.0000

Data Index: 294993 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9868. Min Act: -0.0000

Data Index: 698348 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.0053. Min Range: -1.0053

Max Act: 1.0053. Min Act: -0.0000

Data Index: 25548 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9496. Min Act: -0.0000

Data Index: 433232 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1249837 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8644. Min Act: -0.0000

Data Index: 346396 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8223. Min Act: -0.0000

Data Index: 272678 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7908. Min Act: -0.0000

Data Index: 492314 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1115222 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7812. Min Act: -0.0000

Data Index: 528060 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7794. Min Act: -0.0000

Data Index: 217843 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1209600 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7730. Min Act: -0.0000

Data Index: 790637 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1138077 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7629. Min Act: -0.0000

Data Index: 196848 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1124177 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7920. Min Act: -0.0000

Data Index: 71288 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7777. Min Act: -0.0000

Data Index: 909501 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7024. Min Act: -0.0000

Data Index: 120741 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7576. Min Act: -0.0000

Data Index: 793138 (C4 (Web Text))

Max Activating Token Index: 105