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

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

Neuron 4321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9241. Min Range: -4.9241

Max Act: 4.9241. Min Act: -0.0000

Data Index: 601940 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 4.9241. Min Range: -4.9241

Max Act: 4.2990. Min Act: -0.0000

Data Index: 909141 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.9716. Min Act: -0.0000

Data Index: 1025558 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 4.9241. Min Range: -4.9241

Max Act: 4.0866. Min Act: -0.0000

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 4.9241. Min Range: -4.9241

Max Act: 4.0403. Min Act: -0.0000

Data Index: 218620 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.9963. Min Act: -0.0000

Data Index: 921227 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.8079. Min Act: -0.0000

Data Index: 547208 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.5063. Min Act: -0.0000

Data Index: 380527 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.2912. Min Act: -0.0000

Data Index: 908380 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.2735. Min Act: -0.0000

Data Index: 227932 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.8187. Min Act: -0.0000

Data Index: 393710 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.8983. Min Act: -0.0000

Data Index: 311703 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.9980. Min Act: -0.0000

Data Index: 791706 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 4.9241. Min Range: -4.9241

Max Act: 3.1544. Min Act: -0.0000

Data Index: 116960 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.9817. Min Act: -0.0000

Data Index: 1065754 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1176550 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.6722. Min Act: -0.0000

Data Index: 937956 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.6751. Min Act: -0.0000

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.9416. Min Act: -0.0000

Data Index: 733551 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.9241. Min Range: -4.9241

Max Act: 2.6206. Min Act: -0.0000

Data Index: 1288992 (C4 (Web Text))

Max Activating Token Index: 710