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

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

Neuron 5433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.6691. Min Act: -0.0000

Data Index: 1091869 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.5278. Min Act: -0.0001

Data Index: 929894 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4528. Min Act: -0.0000

Data Index: 247361 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.5496. Min Act: -0.0001

Data Index: 275885 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4982. Min Act: -0.0001

Data Index: 646416 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4452. Min Act: -0.0000

Data Index: 448944 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3840. Min Act: -0.0000

Data Index: 606284 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4711. Min Act: -0.0001

Data Index: 1111943 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4711. Min Act: -0.0000

Data Index: 612899 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3933. Min Act: -0.0000

Data Index: 906521 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1046112 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4097. Min Act: -0.0000

Data Index: 421681 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4997. Min Act: -0.0000

Data Index: 1041715 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4455. Min Act: -0.0001

Data Index: 1168584 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4698. Min Act: -0.0001

Data Index: 499512 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4502. Min Act: -0.0000

Data Index: 426931 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4119. Min Act: -0.0000

Data Index: 894115 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4295. Min Act: -0.0001

Data Index: 590058 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1080773 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1282167 (C4 (Web Text))

Max Activating Token Index: 667