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

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

Neuron 4398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4017. Min Range: -2.4017

Max Act: 2.4017. Min Act: -0.0000

Data Index: 1122651 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.6953. Min Act: -0.0000

Data Index: 511204 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.6850. Min Act: -0.0000

Data Index: 1172248 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1183329 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1011897 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.3739. Min Act: -0.0000

Data Index: 654437 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1124412 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.2163. Min Act: -0.0000

Data Index: 466627 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.2195. Min Act: -0.0000

Data Index: 280788 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1986. Min Act: -0.0000

Data Index: 10841 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1901. Min Act: -0.0000

Data Index: 693961 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1100266 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1626. Min Act: -0.0000

Data Index: 293020 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1637. Min Act: -0.0000

Data Index: 684906 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1133760 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1244536 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1320977 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.1940. Min Act: -0.0000

Data Index: 665470 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.0643. Min Act: -0.0000

Data Index: 350939 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 2.4017. Min Range: -2.4017

Max Act: 1.0421. Min Act: -0.0000

Data Index: 624018 (C4 (Web Text))

Max Activating Token Index: 183