Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0001

Data Index: 608747 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1051875 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1131716 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0864. Min Act: -0.0001

Data Index: 553074 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1281484 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0804. Min Act: -0.0002

Data Index: 768664 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1258524 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0841. Min Act: -0.0001

Data Index: 552491 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0861. Min Act: -0.0001

Data Index: 793662 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0860. Min Act: -0.0001

Data Index: 42410 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0753. Min Act: -0.0002

Data Index: 703650 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0825. Min Act: -0.0002

Data Index: 570418 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0794. Min Act: -0.0002

Data Index: 834423 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0795. Min Act: -0.0002

Data Index: 476238 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1189088 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0818. Min Act: -0.0001

Data Index: 811619 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0817. Min Act: -0.0001

Data Index: 219772 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0794. Min Act: -0.0001

Data Index: 560748 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1352433 (C4 (Web Text))

Max Activating Token Index: 958