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

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

Neuron 992 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: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: -0.0000

Data Index: 145797 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1316149 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1226360 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1143329 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2679. Min Act: -0.0000

Data Index: 929963 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1310950 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2562. Min Act: -0.0000

Data Index: 696422 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1171006 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1344024 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2195. Min Act: -0.0000

Data Index: 763316 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2177. Min Act: -0.0000

Data Index: 831568 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1978. Min Act: -0.0000

Data Index: 234405 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1282260 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1214370 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2137. Min Act: -0.0000

Data Index: 302970 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1289634 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1867. Min Act: -0.0000

Data Index: 722224 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1988. Min Act: -0.0000

Data Index: 883340 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1013025 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1832. Min Act: -0.0000

Data Index: 739622 (C4 (Web Text))

Max Activating Token Index: 239