Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3102. Min Act: -0.0001

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3337. Min Act: -0.0001

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3261. Min Act: -0.0001

Data Index: 377773 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3291. Min Act: -0.0001

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3327. Min Act: -0.0001

Data Index: 1220358 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2848. Min Act: -0.0001

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3022. Min Act: -0.0001

Data Index: 833342 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2857. Min Act: -0.0001

Data Index: 822467 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2750. Min Act: -0.0001

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1531250 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1566926 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3157. Min Act: -0.0001

Data Index: 1464727 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2658. Min Act: -0.0001

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2937. Min Act: -0.0001

Data Index: 199808 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1263906 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2887. Min Act: -0.0001

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2660. Min Act: -0.0001

Data Index: 512623 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1078829 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2752. Min Act: -0.0001

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 608