Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 253 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2555. Min Range: -3.2555

Max Act: 3.2555. Min Act: -0.0001

Data Index: 1092480 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 3.2555. Min Range: -3.2555

Max Act: 3.0653. Min Act: -0.0001

Data Index: 1544855 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.9966. Min Act: -0.0001

Data Index: 1596528 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 3.2555. Min Range: -3.2555

Max Act: 3.0041. Min Act: -0.0001

Data Index: 1635987 (Python Code)

Max Activating Token Index: 491

Text #4

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.9985. Min Act: -0.0001

Data Index: 1405235 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5358. Min Act: -0.0001

Data Index: 1451849 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.7703. Min Act: -0.0001

Data Index: 1437168 (Python Code)

Max Activating Token Index: 947

Text #7

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.6912. Min Act: -0.0001

Data Index: 1470620 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5252. Min Act: -0.0001

Data Index: 1478167 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.6486. Min Act: -0.0001

Data Index: 1599721 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.6082. Min Act: -0.0001

Data Index: 1378925 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5888. Min Act: -0.0001

Data Index: 1614781 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5901. Min Act: -0.0001

Data Index: 1459674 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5509. Min Act: -0.0001

Data Index: 1417073 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5300. Min Act: -0.0001

Data Index: 1586166 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5382. Min Act: -0.0001

Data Index: 1383270 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.4193. Min Act: -0.0001

Data Index: 1631616 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.6512. Min Act: -0.0001

Data Index: 1588528 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.5273. Min Act: -0.0001

Data Index: 1528438 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 3.2555. Min Range: -3.2555

Max Act: 2.3453. Min Act: -0.0001

Data Index: 670544 (C4 (Web Text))

Max Activating Token Index: 246