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

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

Neuron 2972 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3552. Min Act: -0.0001

Data Index: 160781 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3654. Min Act: -0.0001

Data Index: 1288410 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1296607 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1237188 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3184. Min Act: -0.0001

Data Index: 856250 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3577. Min Act: -0.0001

Data Index: 1333915 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1636487 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3482. Min Act: -0.0001

Data Index: 626207 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1023620 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1085207 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3291. Min Act: -0.0001

Data Index: 388163 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3307. Min Act: -0.0001

Data Index: 719803 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3478. Min Act: -0.0001

Data Index: 265822 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3144. Min Act: -0.0001

Data Index: 348019 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1165632 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1202535 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1127540 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1026633 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3054. Min Act: -0.0001

Data Index: 200466 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3164. Min Act: -0.0001

Data Index: 851029 (C4 (Web Text))

Max Activating Token Index: 149