Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4887 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4924. Min Act: -0.0000

Data Index: 333074 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4428. Min Act: -0.0000

Data Index: 390646 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1241102 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3775. Min Act: -0.0000

Data Index: 908178 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1085407 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3772. Min Act: -0.0000

Data Index: 740728 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1166869 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1127697 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3460. Min Act: -0.0000

Data Index: 408484 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3642. Min Act: -0.0000

Data Index: 427344 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3806. Min Act: -0.0000

Data Index: 307222 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3547. Min Act: -0.0000

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3097. Min Act: -0.0000

Data Index: 179278 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1128167 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3382. Min Act: -0.0000

Data Index: 119247 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1040615 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3136. Min Act: -0.0000

Data Index: 40545 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3111. Min Act: -0.0000

Data Index: 193175 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3084. Min Act: -0.0000

Data Index: 881985 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3221. Min Act: -0.0000

Data Index: 197788 (C4 (Web Text))

Max Activating Token Index: 236