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

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

Neuron 1480 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: 1.9500. Min Range: -1.9500

Max Act: 1.9500. Min Act: -0.0000

Data Index: 303470 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.6620. Min Act: -0.0001

Data Index: 1474095 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4780. Min Act: -0.0001

Data Index: 1605632 (Python Code)

Max Activating Token Index: 368

Text #3

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.6374. Min Act: -0.0001

Data Index: 1212963 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.5913. Min Act: -0.0001

Data Index: 225943 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.5497. Min Act: -0.0000

Data Index: 1414197 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.6271. Min Act: -0.0001

Data Index: 1643992 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.5529. Min Act: -0.0001

Data Index: 1611670 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.6203. Min Act: -0.0001

Data Index: 434496 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.5816. Min Act: -0.0001

Data Index: 1600760 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4929. Min Act: -0.0001

Data Index: 1484626 (Python Code)

Max Activating Token Index: 576

Text #11

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.5706. Min Act: -0.0001

Data Index: 871527 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4771. Min Act: -0.0001

Data Index: 1369338 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1585475 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4272. Min Act: -0.0001

Data Index: 807908 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3316. Min Act: -0.0001

Data Index: 403559 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4020. Min Act: -0.0001

Data Index: 939857 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4200. Min Act: -0.0001

Data Index: 100794 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3366. Min Act: -0.0001

Data Index: 200791 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3258. Min Act: -0.0001

Data Index: 1180981 (C4 (Web Text))

Max Activating Token Index: 237