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

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

Neuron 1000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1038577 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.4063. Min Act: -0.0000

Data Index: 432537 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1259353 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1111624 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3346. Min Act: -0.0000

Data Index: 837801 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1163942 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1299182 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2477. Min Act: -0.0000

Data Index: 887684 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2285. Min Act: -0.0000

Data Index: 416781 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2411. Min Act: -0.0000

Data Index: 447126 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2331. Min Act: -0.0000

Data Index: 111065 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2328. Min Act: -0.0000

Data Index: 342480 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1074992 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2310. Min Act: -0.0000

Data Index: 244871 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.1888. Min Act: -0.0000

Data Index: 432836 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2228. Min Act: -0.0000

Data Index: 513195 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2315. Min Act: -0.0000

Data Index: 818561 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1060690 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1155328 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2226. Min Act: -0.0000

Data Index: 693147 (C4 (Web Text))

Max Activating Token Index: 53