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

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

Neuron 87 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.6536. Min Act: -0.0000

Data Index: 83353 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5790. Min Act: -0.0000

Data Index: 209244 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.5311. Min Act: -0.0000

Data Index: 142751 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4930. Min Act: -0.0000

Data Index: 953885 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4767. Min Act: -0.0000

Data Index: 440309 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1230885 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4931. Min Act: -0.0000

Data Index: 521808 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4732. Min Act: 0.0000

Data Index: 721644 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1244417 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1021827 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1224646 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4425. Min Act: -0.0000

Data Index: 761355 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4357. Min Act: -0.0000

Data Index: 862250 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4380. Min Act: -0.0000

Data Index: 957970 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4489. Min Act: -0.0000

Data Index: 929784 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4371. Min Act: -0.0000

Data Index: 492426 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4436. Min Act: -0.0000

Data Index: 491061 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1060691 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4231. Min Act: -0.0000

Data Index: 169886 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.6536. Min Range: -0.6536

Max Act: 0.4364. Min Act: -0.0000

Data Index: 186459 (C4 (Web Text))

Max Activating Token Index: 703