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

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

Neuron 182 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0631. Min Range: -8.0631

Max Act: 8.0631. Min Act: -0.0000

Data Index: 1287579 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 8.0631. Min Range: -8.0631

Max Act: 7.2483. Min Act: -0.0000

Data Index: 1073305 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 8.0631. Min Range: -8.0631

Max Act: 7.1769. Min Act: -0.0000

Data Index: 1098959 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.5204. Min Act: -0.0000

Data Index: 1138672 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.2945. Min Act: -0.0000

Data Index: 692059 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.2103. Min Act: -0.0000

Data Index: 1119738 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.6693. Min Act: -0.0000

Data Index: 1215442 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.0351. Min Act: -0.0000

Data Index: 208940 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.1123. Min Act: -0.0000

Data Index: 1051035 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.5084. Min Act: -0.0000

Data Index: 559381 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.1541. Min Act: -0.0000

Data Index: 440621 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.9085. Min Act: -0.0000

Data Index: 629222 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.8157. Min Act: -0.0000

Data Index: 730987 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.5797. Min Act: -0.0000

Data Index: 335756 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.6772. Min Act: -0.0000

Data Index: 332963 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 8.0631. Min Range: -8.0631

Max Act: 6.2388. Min Act: -0.0000

Data Index: 100118 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.6479. Min Act: -0.0000

Data Index: 297356 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.7829. Min Act: -0.0000

Data Index: 1341703 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.3434. Min Act: -0.0000

Data Index: 250341 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 8.0631. Min Range: -8.0631

Max Act: 5.3454. Min Act: -0.0000

Data Index: 231374 (C4 (Web Text))

Max Activating Token Index: 129