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

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

Neuron 5770 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2531. Min Range: -3.2531

Max Act: 3.2531. Min Act: -0.0000

Data Index: 1469891 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.9563. Min Act: -0.0000

Data Index: 1362550 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.9654. Min Act: -0.0000

Data Index: 1566444 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 3.2531. Min Range: -3.2531

Max Act: 3.2273. Min Act: -0.0000

Data Index: 1498586 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.9090. Min Act: -0.0000

Data Index: 1443906 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.7995. Min Act: -0.0000

Data Index: 1464613 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.5634. Min Act: -0.0000

Data Index: 284501 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.5831. Min Act: -0.0000

Data Index: 1617835 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.5958. Min Act: -0.0000

Data Index: 1106210 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.5476. Min Act: -0.0000

Data Index: 730762 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.4844. Min Act: -0.0000

Data Index: 1584726 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.4176. Min Act: -0.0000

Data Index: 1580325 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.5307. Min Act: -0.0000

Data Index: 1102058 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.3947. Min Act: -0.0000

Data Index: 1359634 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.2333. Min Act: -0.0000

Data Index: 118389 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.3452. Min Act: -0.0000

Data Index: 180775 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.3533. Min Act: -0.0000

Data Index: 628604 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.1900. Min Act: -0.0000

Data Index: 596283 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.3052. Min Act: -0.0000

Data Index: 316671 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.2531. Min Range: -3.2531

Max Act: 2.2584. Min Act: -0.0000

Data Index: 1439315 (Python Code)

Max Activating Token Index: 676