Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1544512 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1435922 (Python Code)

Max Activating Token Index: 231

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1421491 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1439827 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1023573 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0381. Min Act: -0.0002

Data Index: 477273 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0359. Min Act: -0.0002

Data Index: 851157 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0348. Min Act: -0.0002

Data Index: 988979 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0341. Min Act: -0.0002

Data Index: 412681 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1276052 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0338. Min Act: -0.0002

Data Index: 823517 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0338. Min Act: -0.0002

Data Index: 977423 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1052905 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0337. Min Act: -0.0002

Data Index: 739413 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1221863 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1046169 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1454579 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0367. Min Act: -0.0002

Data Index: 375473 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1426628 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1538599 (Python Code)

Max Activating Token Index: 367