Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3674 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1445935 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1033114 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3525. Min Act: 0.0000

Data Index: 1438661 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3366. Min Act: -0.0000

Data Index: 965702 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3238. Min Act: 0.0000

Data Index: 1447284 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1032523 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3294. Min Act: -0.0000

Data Index: 106095 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3146. Min Act: -0.0000

Data Index: 724601 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3280. Min Act: 0.0000

Data Index: 1448752 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1277556 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2788. Min Act: -0.0000

Data Index: 246064 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2806. Min Act: -0.0000

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2914. Min Act: -0.0000

Data Index: 548310 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3106. Min Act: -0.0000

Data Index: 57279 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2944. Min Act: -0.0000

Data Index: 861087 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2973. Min Act: -0.0000

Data Index: 78514 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2803. Min Act: -0.0000

Data Index: 592515 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2671. Min Act: 0.0000

Data Index: 1522274 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2651. Min Act: -0.0000

Data Index: 367079 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2873. Min Act: -0.0000

Data Index: 297418 (C4 (Web Text))

Max Activating Token Index: 933