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

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

Neuron 6 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2854. Min Act: -0.0001

Data Index: 809823 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2953. Min Act: -0.0001

Data Index: 252092 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2525. Min Act: -0.0001

Data Index: 630226 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1146775 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2624. Min Act: -0.0001

Data Index: 754559 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2570. Min Act: -0.0001

Data Index: 581638 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2422. Min Act: -0.0001

Data Index: 391583 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1191422 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2283. Min Act: -0.0001

Data Index: 431678 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2577. Min Act: -0.0001

Data Index: 472405 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1241312 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2664. Min Act: -0.0001

Data Index: 361105 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2451. Min Act: -0.0001

Data Index: 332588 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2248. Min Act: -0.0001

Data Index: 703321 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1315346 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2290. Min Act: -0.0001

Data Index: 1150932 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2285. Min Act: -0.0001

Data Index: 898159 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2274. Min Act: -0.0001

Data Index: 745899 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2346. Min Act: -0.0001

Data Index: 787893 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2502. Min Act: -0.0001

Data Index: 360819 (C4 (Web Text))

Max Activating Token Index: 984