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

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

Neuron 16 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: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0000

Data Index: 351350 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1184130 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1160177 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0482. Min Act: -0.0000

Data Index: 369711 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0490. Min Act: -0.0000

Data Index: 780887 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0457. Min Act: -0.0000

Data Index: 757819 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0475. Min Act: -0.0000

Data Index: 1307047 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0477. Min Act: -0.0000

Data Index: 362295 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0532. Min Act: -0.0000

Data Index: 732473 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0467. Min Act: -0.0000

Data Index: 793256 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1024697 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0431. Min Act: -0.0000

Data Index: 720680 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0473. Min Act: -0.0000

Data Index: 823607 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1278991 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0418. Min Act: -0.0000

Data Index: 780280 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0467. Min Act: -0.0000

Data Index: 866591 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0431. Min Act: -0.0000

Data Index: 982999 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0366. Min Act: -0.0000

Data Index: 789179 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0398. Min Act: -0.0000

Data Index: 49831 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0396. Min Act: -0.0000

Data Index: 307769 (C4 (Web Text))

Max Activating Token Index: 423