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

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

Neuron 1438 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.3371. Min Act: -0.0001

Data Index: 970450 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2825. Min Act: -0.0001

Data Index: 696529 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2646. Min Act: -0.0001

Data Index: 229214 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2724. Min Act: -0.0001

Data Index: 282646 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2669. Min Act: -0.0001

Data Index: 390881 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1072384 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2635. Min Act: -0.0001

Data Index: 160799 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1106117 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2568. Min Act: -0.0001

Data Index: 357743 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2591. Min Act: -0.0001

Data Index: 18256 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2511. Min Act: -0.0001

Data Index: 845347 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2456. Min Act: -0.0001

Data Index: 761567 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2470. Min Act: -0.0001

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2667. Min Act: -0.0001

Data Index: 562686 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2519. Min Act: -0.0001

Data Index: 581344 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2518. Min Act: -0.0001

Data Index: 432229 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2729. Min Act: -0.0001

Data Index: 6151 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2489. Min Act: -0.0001

Data Index: 911714 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2545. Min Act: -0.0001

Data Index: 416474 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.3371. Min Range: -0.3371

Max Act: 0.2462. Min Act: -0.0001

Data Index: 1092202 (C4 (Web Text))

Max Activating Token Index: 527