Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0396. Min Range: -1.0396

Max Act: 1.0086. Min Act: -0.0000

Data Index: 768023 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1088865 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 1.0396. Min Range: -1.0396

Max Act: 1.0396. Min Act: -0.0001

Data Index: 708381 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9825. Min Act: -0.0001

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8874. Min Act: -0.0001

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8626. Min Act: -0.0001

Data Index: 690992 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8801. Min Act: -0.0001

Data Index: 291653 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8761. Min Act: -0.0000

Data Index: 924426 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8680. Min Act: -0.0001

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1251688 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8321. Min Act: -0.0001

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7948. Min Act: -0.0001

Data Index: 180098 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1283751 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7490. Min Act: -0.0001

Data Index: 1310434 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8043. Min Act: -0.0001

Data Index: 627029 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7326. Min Act: -0.0000

Data Index: 253147 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1024694 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7800. Min Act: -0.0001

Data Index: 782619 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7378. Min Act: -0.0001

Data Index: 652979 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7080. Min Act: -0.0000

Data Index: 430074 (C4 (Web Text))

Max Activating Token Index: 947