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

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

Neuron 2704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1293729 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2962. Min Act: -0.0000

Data Index: 408077 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2788. Min Act: -0.0000

Data Index: 720891 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2576. Min Act: -0.0000

Data Index: 661951 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2434. Min Act: -0.0000

Data Index: 554624 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2366. Min Act: -0.0000

Data Index: 775067 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1654162 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1436907 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1209515 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1921. Min Act: -0.0000

Data Index: 139107 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2225. Min Act: -0.0000

Data Index: 645615 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2193. Min Act: -0.0000

Data Index: 10693 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2197. Min Act: -0.0000

Data Index: 936418 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1224198 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2126. Min Act: -0.0000

Data Index: 444201 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1920. Min Act: -0.0000

Data Index: 632741 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1891. Min Act: -0.0000

Data Index: 768597 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1185438 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1799. Min Act: -0.0000

Data Index: 877600 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1917. Min Act: -0.0000

Data Index: 297424 (C4 (Web Text))

Max Activating Token Index: 320