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

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

Neuron 2278 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: 1.3397. Min Range: -1.3397

Max Act: 1.1264. Min Act: -0.0000

Data Index: 183267 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.3397. Min Range: -1.3397

Max Act: 1.3397. Min Act: -0.0000

Data Index: 278666 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.3397. Min Range: -1.3397

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1096244 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.3397. Min Range: -1.3397

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1250646 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1204281 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.3397. Min Range: -1.3397

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1313114 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9496. Min Act: -0.0000

Data Index: 318600 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9545. Min Act: -0.0000

Data Index: 809932 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1182340 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9090. Min Act: -0.0000

Data Index: 470826 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.3397. Min Range: -1.3397

Max Act: 1.0726. Min Act: -0.0000

Data Index: 392973 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1220638 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9514. Min Act: -0.0000

Data Index: 813738 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9036. Min Act: -0.0000

Data Index: 323235 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.3397. Min Range: -1.3397

Max Act: 1.0578. Min Act: -0.0000

Data Index: 957025 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1203300 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9206. Min Act: -0.0000

Data Index: 562293 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9220. Min Act: -0.0000

Data Index: 208292 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1254170 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 1.3397. Min Range: -1.3397

Max Act: 0.9547. Min Act: -0.0000

Data Index: 957818 (C4 (Web Text))

Max Activating Token Index: 280