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

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

Neuron 5775 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: 0.4516. Min Range: -0.4516

Max Act: 0.4516. Min Act: -0.0000

Data Index: 741421 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4212. Min Act: -0.0000

Data Index: 919188 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4225. Min Act: -0.0000

Data Index: 684498 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1439707 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4061. Min Act: -0.0000

Data Index: 297641 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3980. Min Act: -0.0000

Data Index: 971506 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1614310 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3682. Min Act: -0.0000

Data Index: 277492 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1554483 (Python Code)

Max Activating Token Index: 812

Text #9

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1594392 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1433987 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1388266 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1523491 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1574027 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1444971 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1574215 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1493212 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1479097 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1396257 (Python Code)

Max Activating Token Index: 65