Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 60 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.6203. Min Act: -0.0001

Data Index: 907528 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5006. Min Act: -0.0001

Data Index: 822554 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.4324. Min Act: -0.0001

Data Index: 199470 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5225. Min Act: -0.0001

Data Index: 1267274 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.3904. Min Act: -0.0001

Data Index: 1133933 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.3302. Min Act: -0.0001

Data Index: 992153 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.1072. Min Act: -0.0001

Data Index: 252701 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.4477. Min Act: -0.0001

Data Index: 118661 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.3510. Min Act: -0.0001

Data Index: 1178555 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.1192. Min Act: -0.0001

Data Index: 76554 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.1011. Min Act: -0.0001

Data Index: 580360 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.4091. Min Act: -0.0001

Data Index: 287848 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.3485. Min Act: -0.0001

Data Index: 1244557 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.2315. Min Act: -0.0001

Data Index: 264175 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.2690. Min Act: -0.0001

Data Index: 1357721 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.2343. Min Act: -0.0001

Data Index: 88230 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.0474. Min Act: -0.0001

Data Index: 1165482 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.1208. Min Act: -0.0001

Data Index: 975368 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.1511. Min Act: -0.0001

Data Index: 84811 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.3002. Min Act: -0.0001

Data Index: 665713 (C4 (Web Text))

Max Activating Token Index: 788