Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1593 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.8492. Min Act: -0.0000

Data Index: 746925 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.8196. Min Act: -0.0000

Data Index: 273425 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.6787. Min Act: -0.0001

Data Index: 19304 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.5351. Min Act: -0.0001

Data Index: 44381 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.4863. Min Act: -0.0001

Data Index: 1005069 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.4735. Min Act: -0.0000

Data Index: 213234 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3362. Min Act: -0.0000

Data Index: 405382 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3326. Min Act: -0.0001

Data Index: 1232000 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3971. Min Act: -0.0001

Data Index: 605186 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3839. Min Act: -0.0000

Data Index: 924432 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.4608. Min Act: -0.0000

Data Index: 572492 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3634. Min Act: -0.0000

Data Index: 630295 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3353. Min Act: -0.0000

Data Index: 752710 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3168. Min Act: -0.0000

Data Index: 473121 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3147. Min Act: -0.0001

Data Index: 36369 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.3040. Min Act: -0.0000

Data Index: 832029 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.2925. Min Act: -0.0000

Data Index: 437719 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.2272. Min Act: -0.0000

Data Index: 807756 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.1965. Min Act: -0.0000

Data Index: 52722 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.8492. Min Range: -1.8492

Max Act: 1.2469. Min Act: -0.0000

Data Index: 988100 (C4 (Web Text))

Max Activating Token Index: 90