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

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

Neuron 3933 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5720. Min Act: -0.0000

Data Index: 659160 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1353567 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4834. Min Act: -0.0000

Data Index: 70826 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1173852 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4375. Min Act: -0.0001

Data Index: 1364055 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4681. Min Act: -0.0001

Data Index: 40868 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4620. Min Act: -0.0001

Data Index: 655996 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4250. Min Act: -0.0001

Data Index: 625585 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4388. Min Act: -0.0001

Data Index: 506026 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4336. Min Act: -0.0000

Data Index: 728796 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4186. Min Act: -0.0001

Data Index: 138172 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1092352 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4359. Min Act: -0.0000

Data Index: 390152 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4299. Min Act: -0.0001

Data Index: 67365 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1157733 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1065508 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.4074. Min Act: -0.0001

Data Index: 173396 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3739. Min Act: -0.0000

Data Index: 324418 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3789. Min Act: -0.0001

Data Index: 261686 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.5720. Min Range: -0.5720

Max Act: 0.3883. Min Act: -0.0001

Data Index: 226423 (C4 (Web Text))

Max Activating Token Index: 974