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

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

Neuron 2114 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4841. Min Act: -0.0001

Data Index: 909594 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4677. Min Act: -0.0001

Data Index: 1113518 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4657. Min Act: -0.0001

Data Index: 314663 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4507. Min Act: -0.0001

Data Index: 531793 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4488. Min Act: -0.0001

Data Index: 26840 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4377. Min Act: -0.0002

Data Index: 953996 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4450. Min Act: -0.0001

Data Index: 492651 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4421. Min Act: -0.0001

Data Index: 72674 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4377. Min Act: -0.0001

Data Index: 314156 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4443. Min Act: -0.0001

Data Index: 908156 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4343. Min Act: -0.0001

Data Index: 93872 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4347. Min Act: -0.0001

Data Index: 706771 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1333623 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4400. Min Act: -0.0001

Data Index: 354747 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4384. Min Act: -0.0001

Data Index: 987004 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4287. Min Act: -0.0001

Data Index: 297343 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4266. Min Act: -0.0001

Data Index: 1071222 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4378. Min Act: -0.0001

Data Index: 513411 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4257. Min Act: -0.0001

Data Index: 959734 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4389. Min Act: -0.0001

Data Index: 202564 (C4 (Web Text))

Max Activating Token Index: 412