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

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

Neuron 4660 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: 0.1107. Min Range: -0.1107

Max Act: 0.1088. Min Act: -0.0002

Data Index: 592270 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.1107. Min Act: -0.0002

Data Index: 387139 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0981. Min Act: -0.0003

Data Index: 1029148 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0963. Min Act: -0.0002

Data Index: 60438 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0947. Min Act: -0.0002

Data Index: 789345 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0922. Min Act: -0.0003

Data Index: 773677 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0893. Min Act: -0.0002

Data Index: 482607 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0923. Min Act: -0.0002

Data Index: 990795 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0910. Min Act: -0.0002

Data Index: 259704 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1024910 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0877. Min Act: -0.0002

Data Index: 132377 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0837. Min Act: -0.0002

Data Index: 241647 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0844. Min Act: -0.0003

Data Index: 207998 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0832. Min Act: -0.0002

Data Index: 686435 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0808. Min Act: -0.0002

Data Index: 822744 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0807. Min Act: -0.0002

Data Index: 178051 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0790. Min Act: -0.0002

Data Index: 497432 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0788. Min Act: -0.0002

Data Index: 556413 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0771. Min Act: -0.0003

Data Index: 615554 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.1107. Min Range: -0.1107

Max Act: 0.0761. Min Act: -0.0003

Data Index: 694766 (C4 (Web Text))

Max Activating Token Index: 41