Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 255 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1332753 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1005694 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.7323. Min Act: -0.0000

Data Index: 207140 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5566. Min Act: -0.0000

Data Index: 652271 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5654. Min Act: -0.0000

Data Index: 310859 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5535. Min Act: -0.0000

Data Index: 923236 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5709. Min Act: -0.0000

Data Index: 660567 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5357. Min Act: -0.0000

Data Index: 370369 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5107. Min Act: -0.0000

Data Index: 140885 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1236982 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5763. Min Act: -0.0000

Data Index: 286850 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5272. Min Act: -0.0000

Data Index: 547970 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.4672. Min Act: -0.0000

Data Index: 858248 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.4899. Min Act: -0.0000

Data Index: 234443 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1124379 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1221920 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5185. Min Act: -0.0000

Data Index: 322134 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.4541. Min Act: -0.0000

Data Index: 777384 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5410. Min Act: -0.0000

Data Index: 421887 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.8291. Min Range: -0.8291

Max Act: 0.5033. Min Act: -0.0000

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 461