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

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

Neuron 3296 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: 0.5295. Min Range: -0.5295

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1283474 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.5295. Min Act: -0.0001

Data Index: 149271 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1116896 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3569. Min Act: -0.0000

Data Index: 49028 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3544. Min Act: -0.0000

Data Index: 856100 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3437. Min Act: -0.0000

Data Index: 321158 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3211. Min Act: -0.0000

Data Index: 88884 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1049830 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3325. Min Act: -0.0000

Data Index: 913087 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3280. Min Act: -0.0000

Data Index: 812995 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3140. Min Act: -0.0001

Data Index: 305024 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1114865 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3067. Min Act: -0.0000

Data Index: 631131 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1198944 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1109511 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3603. Min Act: -0.0000

Data Index: 844987 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3339. Min Act: -0.0000

Data Index: 259815 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1303349 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3058. Min Act: -0.0000

Data Index: 139831 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3019. Min Act: -0.0001

Data Index: 838485 (C4 (Web Text))

Max Activating Token Index: 532