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

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

Neuron 2670 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0792. Min Range: -1.0792

Max Act: 1.0758. Min Act: -0.0002

Data Index: 1346644 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 1.0792. Min Range: -1.0792

Max Act: 1.0792. Min Act: -0.0002

Data Index: 237618 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.0792. Min Range: -1.0792

Max Act: 1.0285. Min Act: -0.0002

Data Index: 564123 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9754. Min Act: -0.0002

Data Index: 676877 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9863. Min Act: -0.0002

Data Index: 252305 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9715. Min Act: -0.0002

Data Index: 932122 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9659. Min Act: -0.0002

Data Index: 595684 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9586. Min Act: -0.0002

Data Index: 881075 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9163. Min Act: -0.0002

Data Index: 776084 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9152. Min Act: -0.0002

Data Index: 12687 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9349. Min Act: -0.0002

Data Index: 526904 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9130. Min Act: -0.0002

Data Index: 699591 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.8991. Min Act: -0.0002

Data Index: 1139161 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9061. Min Act: -0.0002

Data Index: 329994 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9088. Min Act: -0.0002

Data Index: 562016 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.8991. Min Act: -0.0002

Data Index: 100167 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.8942. Min Act: -0.0002

Data Index: 1120933 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.8786. Min Act: -0.0002

Data Index: 658805 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.8906. Min Act: -0.0002

Data Index: 783558 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.0792. Min Range: -1.0792

Max Act: 0.9050. Min Act: -0.0002

Data Index: 484658 (C4 (Web Text))

Max Activating Token Index: 711