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

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

Neuron 2905 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: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0002

Data Index: 335267 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0861. Min Act: -0.0002

Data Index: 797560 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0867. Min Act: -0.0002

Data Index: 244057 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1306710 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0850. Min Act: -0.0002

Data Index: 3579 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0838. Min Act: -0.0002

Data Index: 471936 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0825. Min Act: -0.0002

Data Index: 870572 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0807. Min Act: -0.0002

Data Index: 345210 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1187362 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0802. Min Act: -0.0002

Data Index: 162634 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1582168 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0815. Min Act: -0.0002

Data Index: 997505 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0808. Min Act: -0.0002

Data Index: 298404 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0778. Min Act: -0.0002

Data Index: 989882 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0779. Min Act: -0.0002

Data Index: 399867 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1049509 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0775. Min Act: -0.0002

Data Index: 455741 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1588428 (Python Code)

Max Activating Token Index: 145

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1301228 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1223821 (C4 (Web Text))

Max Activating Token Index: 342