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

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

Neuron 4402 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: 0.4148. Min Range: -0.4148

Max Act: 0.4148. Min Act: -0.0000

Data Index: 200692 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3947. Min Act: -0.0000

Data Index: 787422 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1367817 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1076708 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3518. Min Act: -0.0000

Data Index: 108985 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3461. Min Act: -0.0000

Data Index: 824627 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3312. Min Act: -0.0000

Data Index: 54200 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3553. Min Act: -0.0000

Data Index: 8557 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1159950 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3252. Min Act: -0.0000

Data Index: 834313 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1338993 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3404. Min Act: -0.0000

Data Index: 717899 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3025. Min Act: -0.0000

Data Index: 195125 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3121. Min Act: -0.0000

Data Index: 865925 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3031. Min Act: -0.0000

Data Index: 145151 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.3089. Min Act: -0.0000

Data Index: 9492 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2902. Min Act: -0.0000

Data Index: 50782 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1364296 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2885. Min Act: -0.0000

Data Index: 34683 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.4148. Min Range: -0.4148

Max Act: 0.2717. Min Act: -0.0000

Data Index: 677732 (C4 (Web Text))

Max Activating Token Index: 654