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

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

Neuron 3728 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1110774 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.2027. Min Act: -0.0001

Data Index: 630168 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1958. Min Act: -0.0001

Data Index: 932339 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1622. Min Act: -0.0002

Data Index: 527145 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1773. Min Act: -0.0001

Data Index: 699018 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1677. Min Act: -0.0001

Data Index: 1052560 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1530. Min Act: -0.0001

Data Index: 789102 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1259353 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1407. Min Act: -0.0002

Data Index: 1272516 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1456. Min Act: -0.0001

Data Index: 904939 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1399. Min Act: -0.0001

Data Index: 566242 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1326. Min Act: -0.0001

Data Index: 641449 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1373. Min Act: -0.0001

Data Index: 857066 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1303. Min Act: -0.0001

Data Index: 966230 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1469. Min Act: -0.0001

Data Index: 283939 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1289. Min Act: -0.0001

Data Index: 143238 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1362. Min Act: -0.0001

Data Index: 233064 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1423. Min Act: -0.0001

Data Index: 466967 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.2393. Min Range: -0.2393

Max Act: 0.1456. Min Act: -0.0002

Data Index: 504390 (C4 (Web Text))

Max Activating Token Index: 872