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

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

Neuron 4050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.7001. Min Act: -0.0000

Data Index: 191485 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.3180. Min Act: -0.0000

Data Index: 503653 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.4214. Min Act: -0.0001

Data Index: 800565 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.1608. Min Act: -0.0000

Data Index: 1238261 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.0276. Min Act: -0.0001

Data Index: 791073 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.1231. Min Act: -0.0001

Data Index: 1234247 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.1056. Min Act: -0.0000

Data Index: 859013 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.9928. Min Act: -0.0001

Data Index: 1220295 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.1002. Min Act: -0.0000

Data Index: 4925 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.9936. Min Act: -0.0000

Data Index: 283273 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.0567. Min Act: -0.0000

Data Index: 924322 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.8465. Min Act: -0.0001

Data Index: 888786 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.1977. Min Act: -0.0000

Data Index: 422083 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.9840. Min Act: -0.0000

Data Index: 185159 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.0595. Min Act: -0.0000

Data Index: 999566 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.8507. Min Act: -0.0001

Data Index: 974280 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.8353. Min Act: -0.0001

Data Index: 806534 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.3409. Min Act: -0.0000

Data Index: 556392 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 2.7001. Min Range: -2.7001

Max Act: 2.0572. Min Act: -0.0000

Data Index: 698259 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 2.7001. Min Range: -2.7001

Max Act: 1.9180. Min Act: -0.0001

Data Index: 197450 (C4 (Web Text))

Max Activating Token Index: 317