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

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

Neuron 3026 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: 1.2621. Min Range: -1.2621

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1271723 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.2496. Min Act: -0.0000

Data Index: 593448 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.0936. Min Act: -0.0000

Data Index: 832949 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.2621. Min Range: -1.2621

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1119757 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.9924. Min Act: -0.0000

Data Index: 696238 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1100762 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.9366. Min Act: -0.0000

Data Index: 934944 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8690. Min Act: -0.0000

Data Index: 586870 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8868. Min Act: -0.0000

Data Index: 151014 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1063236 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8268. Min Act: -0.0000

Data Index: 630780 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8043. Min Act: -0.0000

Data Index: 145983 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.9193. Min Act: -0.0000

Data Index: 418899 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8642. Min Act: -0.0000

Data Index: 523315 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1047749 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8143. Min Act: -0.0000

Data Index: 838342 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8792. Min Act: -0.0000

Data Index: 276231 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1136662 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.8068. Min Act: -0.0000

Data Index: 925708 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.2621. Min Range: -1.2621

Max Act: 0.7763. Min Act: -0.0000

Data Index: 595707 (C4 (Web Text))

Max Activating Token Index: 23