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

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

Neuron 4217 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1761. Min Range: -1.1761

Max Act: 1.1761. Min Act: -0.0001

Data Index: 1146227 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1290008 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8036. Min Act: -0.0001

Data Index: 910279 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8691. Min Act: -0.0001

Data Index: 1325697 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8430. Min Act: -0.0001

Data Index: 450388 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8562. Min Act: -0.0001

Data Index: 1102945 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6855. Min Act: -0.0001

Data Index: 450607 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.8174. Min Act: -0.0001

Data Index: 124451 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.7214. Min Act: -0.0001

Data Index: 420110 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6663. Min Act: -0.0001

Data Index: 1044968 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1105646 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.5857. Min Act: -0.0001

Data Index: 79987 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.5652. Min Act: -0.0001

Data Index: 402146 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6359. Min Act: -0.0001

Data Index: 789240 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.5486. Min Act: -0.0001

Data Index: 264018 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6193. Min Act: -0.0001

Data Index: 1073307 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.6177. Min Act: -0.0001

Data Index: 299070 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.5415. Min Act: -0.0001

Data Index: 1239685 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.5854. Min Act: -0.0001

Data Index: 1335806 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.1761. Min Range: -1.1761

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1276862 (C4 (Web Text))

Max Activating Token Index: 353