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

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

Neuron 5127 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: 0.3739. Min Range: -0.3739

Max Act: 0.3739. Min Act: -0.0000

Data Index: 229624 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3403. Min Act: -0.0000

Data Index: 16943 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3535. Min Act: -0.0000

Data Index: 183498 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3442. Min Act: -0.0000

Data Index: 440233 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3535. Min Act: -0.0000

Data Index: 790725 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3341. Min Act: -0.0000

Data Index: 263060 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3487. Min Act: -0.0000

Data Index: 672460 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3364. Min Act: -0.0000

Data Index: 179996 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3577. Min Act: -0.0000

Data Index: 458607 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3433. Min Act: -0.0000

Data Index: 505027 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3265. Min Act: -0.0000

Data Index: 722771 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3257. Min Act: -0.0000

Data Index: 201104 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1130237 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3455. Min Act: -0.0000

Data Index: 546910 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1293500 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1265951 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3337. Min Act: -0.0000

Data Index: 169241 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3423. Min Act: -0.0000

Data Index: 300981 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3184. Min Act: -0.0000

Data Index: 86551 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3162. Min Act: -0.0000

Data Index: 741668 (C4 (Web Text))

Max Activating Token Index: 660