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

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

Neuron 907 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: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0002

Data Index: 752283 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1649160 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0911. Min Act: -0.0002

Data Index: 725753 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1488615 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1488279 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0897. Min Act: -0.0002

Data Index: 414943 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1369398 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1567089 (Python Code)

Max Activating Token Index: 1001

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1457785 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1626474 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0839. Min Act: -0.0002

Data Index: 442132 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0834. Min Act: -0.0002

Data Index: 29859 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0844. Min Act: -0.0002

Data Index: 9761 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1496690 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0831. Min Act: -0.0002

Data Index: 92622 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1544209 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0821. Min Act: -0.0002

Data Index: 385270 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1011190 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1283989 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1380387 (Python Code)

Max Activating Token Index: 586