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

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

Neuron 788 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7522. Min Act: -0.0000

Data Index: 626389 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1264528 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1242585 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1166827 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1098428 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6592. Min Act: -0.0000

Data Index: 675186 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6566. Min Act: -0.0000

Data Index: 701908 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1208648 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6226. Min Act: -0.0000

Data Index: 863961 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1192402 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6203. Min Act: -0.0000

Data Index: 659612 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1124217 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6261. Min Act: -0.0000

Data Index: 858608 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6572. Min Act: -0.0000

Data Index: 685555 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6075. Min Act: -0.0000

Data Index: 380456 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6291. Min Act: -0.0000

Data Index: 299519 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6407. Min Act: -0.0000

Data Index: 840142 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1353141 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6038. Min Act: -0.0000

Data Index: 309103 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5595. Min Act: -0.0000

Data Index: 252105 (C4 (Web Text))

Max Activating Token Index: 756