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

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

Neuron 2220 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0001

Data Index: 137919 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1474757 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0359. Min Act: -0.0001

Data Index: 310067 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1493814 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0358. Min Act: -0.0001

Data Index: 687551 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0371. Min Act: -0.0001

Data Index: 259100 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1389185 (Python Code)

Max Activating Token Index: 329

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0340. Min Act: -0.0001

Data Index: 9413 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1385618 (Python Code)

Max Activating Token Index: 329

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0001

Data Index: 146229 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0333. Min Act: -0.0001

Data Index: 799685 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1594211 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0359. Min Act: -0.0001

Data Index: 964726 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1259360 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1547421 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0328. Min Act: -0.0001

Data Index: 398653 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0316. Min Act: -0.0001

Data Index: 208557 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1649416 (Python Code)

Max Activating Token Index: 377

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1448150 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1479683 (Python Code)

Max Activating Token Index: 458