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

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

Neuron 3620 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6350. Min Range: -5.6350

Max Act: 5.6350. Min Act: -0.0000

Data Index: 374442 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 5.6350. Min Range: -5.6350

Max Act: 5.6318. Min Act: -0.0000

Data Index: 382224 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 5.6350. Min Range: -5.6350

Max Act: 5.2808. Min Act: -0.0000

Data Index: 704774 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 5.6350. Min Range: -5.6350

Max Act: 5.4519. Min Act: -0.0000

Data Index: 437046 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 5.6350. Min Range: -5.6350

Max Act: 4.7591. Min Act: -0.0000

Data Index: 1263345 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 5.6350. Min Range: -5.6350

Max Act: 5.0269. Min Act: -0.0000

Data Index: 192732 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 5.6350. Min Range: -5.6350

Max Act: 4.4996. Min Act: -0.0000

Data Index: 1220705 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 5.6350. Min Range: -5.6350

Max Act: 3.3854. Min Act: -0.0000

Data Index: 789885 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.9916. Min Act: -0.0000

Data Index: 17897 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.6624. Min Act: -0.0000

Data Index: 1314551 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.7691. Min Act: -0.0000

Data Index: 864245 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.7978. Min Act: -0.0000

Data Index: 1094561 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.6290. Min Act: -0.0000

Data Index: 312617 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.6031. Min Act: -0.0000

Data Index: 642694 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.5969. Min Act: -0.0000

Data Index: 1344130 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.5721. Min Act: -0.0000

Data Index: 713064 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.6893. Min Act: -0.0000

Data Index: 332871 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.7980. Min Act: -0.0000

Data Index: 345389 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.5891. Min Act: -0.0000

Data Index: 1222865 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 5.6350. Min Range: -5.6350

Max Act: 2.7281. Min Act: -0.0000

Data Index: 1123548 (C4 (Web Text))

Max Activating Token Index: 847