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

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

Neuron 544 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: 4.5377. Min Range: -4.5377

Max Act: 4.5377. Min Act: -0.0000

Data Index: 17830 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 4.5377. Min Range: -4.5377

Max Act: 4.0810. Min Act: -0.0000

Data Index: 787223 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.8907. Min Act: -0.0000

Data Index: 1151248 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.7440. Min Act: -0.0000

Data Index: 945244 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.7525. Min Act: -0.0000

Data Index: 401085 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.3353. Min Act: -0.0000

Data Index: 1143902 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.1610. Min Act: -0.0000

Data Index: 1335856 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.3038. Min Act: -0.0000

Data Index: 898327 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.2620. Min Act: -0.0000

Data Index: 574206 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.1062. Min Act: -0.0000

Data Index: 286285 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.2073. Min Act: -0.0000

Data Index: 286033 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.0338. Min Act: -0.0000

Data Index: 675330 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 4.5377. Min Range: -4.5377

Max Act: 3.0418. Min Act: -0.0000

Data Index: 1084446 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.9089. Min Act: -0.0000

Data Index: 976176 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.9982. Min Act: -0.0000

Data Index: 509585 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.9660. Min Act: -0.0000

Data Index: 561047 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.5433. Min Act: -0.0000

Data Index: 432339 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.9480. Min Act: -0.0000

Data Index: 36499 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.9334. Min Act: -0.0000

Data Index: 661919 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 4.5377. Min Range: -4.5377

Max Act: 2.9410. Min Act: -0.0000

Data Index: 1095578 (C4 (Web Text))

Max Activating Token Index: 12