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

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

Neuron 3004 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2455. Min Range: -2.2455

Max Act: 2.2455. Min Act: -0.0000

Data Index: 340599 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 2.2455. Min Range: -2.2455

Max Act: 2.0173. Min Act: -0.0000

Data Index: 754721 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.7103. Min Act: -0.0000

Data Index: 923716 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.6798. Min Act: -0.0000

Data Index: 607045 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.5718. Min Act: 0.0000

Data Index: 442808 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.4916. Min Act: -0.0000

Data Index: 707936 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1205753 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.5479. Min Act: -0.0000

Data Index: 865618 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1359047 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.3921. Min Act: 0.0000

Data Index: 642303 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.3808. Min Act: 0.0000

Data Index: 829286 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1223434 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1303512 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.3102. Min Act: -0.0000

Data Index: 303828 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.2854. Min Act: -0.0000

Data Index: 86336 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1055720 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1149837 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.2614. Min Act: 0.0000

Data Index: 633891 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.2529. Min Act: -0.0000

Data Index: 900310 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 2.2455. Min Range: -2.2455

Max Act: 1.2440. Min Act: -0.0000

Data Index: 344388 (C4 (Web Text))

Max Activating Token Index: 284