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

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

Neuron 984 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.4220. Min Act: -0.0000

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.4172. Min Act: -0.0001

Data Index: 1470965 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1358810 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3842. Min Act: -0.0000

Data Index: 948957 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.4463. Min Act: -0.0000

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3988. Min Act: -0.0000

Data Index: 824225 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.4019. Min Act: -0.0000

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1475346 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1497729 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3449. Min Act: -0.0001

Data Index: 1608786 (Python Code)

Max Activating Token Index: 687

Text #11

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1426407 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3492. Min Act: -0.0000

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1523040 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1582818 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3089. Min Act: -0.0000

Data Index: 958441 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1369977 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3397. Min Act: -0.0001

Data Index: 3632 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3220. Min Act: -0.0001

Data Index: 1509076 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 0.4463. Min Range: -0.4463

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1652614 (Python Code)

Max Activating Token Index: 777