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

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

Neuron 3788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.9296. Min Act: -0.0001

Data Index: 1218821 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.6596. Min Act: -0.0001

Data Index: 162263 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.7283. Min Act: -0.0001

Data Index: 1334859 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.6365. Min Act: -0.0001

Data Index: 1247784 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.6246. Min Act: -0.0001

Data Index: 1141066 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.5322. Min Act: -0.0001

Data Index: 987178 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.3021. Min Act: -0.0001

Data Index: 890899 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2760. Min Act: -0.0001

Data Index: 1196200 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2533. Min Act: -0.0001

Data Index: 774378 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2994. Min Act: -0.0001

Data Index: 538781 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2925. Min Act: -0.0000

Data Index: 943619 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.1538. Min Act: -0.0001

Data Index: 501154 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2138. Min Act: -0.0001

Data Index: 761815 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.3353. Min Act: -0.0000

Data Index: 609118 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2693. Min Act: -0.0001

Data Index: 744020 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.1809. Min Act: -0.0001

Data Index: 132171 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.2603. Min Act: -0.0001

Data Index: 437619 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.3862. Min Act: -0.0001

Data Index: 390876 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.1716. Min Act: -0.0001

Data Index: 683835 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.9296. Min Range: -1.9296

Max Act: 1.1606. Min Act: -0.0001

Data Index: 943262 (C4 (Web Text))

Max Activating Token Index: 313