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

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

Neuron 4017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1526215 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3762. Min Act: -0.0001

Data Index: 1402276 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3289. Min Act: -0.0001

Data Index: 656014 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3055. Min Act: -0.0001

Data Index: 1615423 (Python Code)

Max Activating Token Index: 420

Text #4

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1373039 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1381355 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1611066 (Python Code)

Max Activating Token Index: 666

Text #7

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1463850 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2891. Min Act: -0.0001

Data Index: 646068 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2522. Min Act: -0.0001

Data Index: 610115 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1551675 (Python Code)

Max Activating Token Index: 553

Text #11

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2349. Min Act: -0.0000

Data Index: 575188 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1489418 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1375359 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1593973 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2552. Min Act: -0.0000

Data Index: 859129 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1602638 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2382. Min Act: -0.0000

Data Index: 511821 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1086234 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2375. Min Act: -0.0001

Data Index: 273646 (C4 (Web Text))

Max Activating Token Index: 813