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

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

Neuron 1586 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7674. Min Act: 0.0000

Data Index: 852457 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1351249 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5833. Min Act: -0.0000

Data Index: 710475 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4838. Min Act: -0.0000

Data Index: 301016 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2922. Min Act: -0.0000

Data Index: 161158 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2486. Min Act: -0.0000

Data Index: 79310 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.1701. Min Act: -0.0000

Data Index: 955367 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0925. Min Act: -0.0000

Data Index: 916785 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1263566 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1255117 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0593. Min Act: -0.0000

Data Index: 754517 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.1031. Min Act: -0.0000

Data Index: 842126 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1339630 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0245. Min Act: -0.0000

Data Index: 661766 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0445. Min Act: -0.0000

Data Index: 570938 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.7674. Min Range: -1.7674

Max Act: 0.9576. Min Act: -0.0000

Data Index: 797816 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.7674. Min Range: -1.7674

Max Act: 0.9401. Min Act: -0.0000

Data Index: 597911 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.7674. Min Range: -1.7674

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1276157 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.7674. Min Range: -1.7674

Max Act: 0.9006. Min Act: -0.0000

Data Index: 913418 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.0161. Min Act: -0.0000

Data Index: 306549 (C4 (Web Text))

Max Activating Token Index: 996