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

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

Neuron 5839 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0000

Data Index: 706935 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1171. Min Act: -0.0000

Data Index: 523841 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1236094 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1121. Min Act: -0.0000

Data Index: 454257 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1086. Min Act: -0.0000

Data Index: 831747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1030917 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1021328 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1093. Min Act: -0.0000

Data Index: 467507 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1052. Min Act: -0.0000

Data Index: 704808 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1058. Min Act: -0.0000

Data Index: 357567 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0998. Min Act: -0.0000

Data Index: 395995 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1026. Min Act: -0.0000

Data Index: 501825 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0969. Min Act: -0.0000

Data Index: 20119 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1001. Min Act: -0.0000

Data Index: 362577 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1316401 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1025. Min Act: -0.0000

Data Index: 596980 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1022. Min Act: -0.0000

Data Index: 303866 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0980. Min Act: -0.0000

Data Index: 597602 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0978. Min Act: -0.0000

Data Index: 589033 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0938. Min Act: -0.0000

Data Index: 416536 (C4 (Web Text))

Max Activating Token Index: 807