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

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

Neuron 2765 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8673. Min Range: -2.8673

Max Act: 2.8673. Min Act: -0.0000

Data Index: 518512 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 2.8673. Min Range: -2.8673

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1274596 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.9524. Min Act: -0.0000

Data Index: 710081 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 2.8673. Min Range: -2.8673

Max Act: 2.0360. Min Act: -0.0000

Data Index: 87594 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 2.8673. Min Range: -2.8673

Max Act: 2.0055. Min Act: -0.0000

Data Index: 747953 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.9590. Min Act: -0.0000

Data Index: 496141 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.9955. Min Act: -0.0000

Data Index: 890068 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.8638. Min Act: -0.0000

Data Index: 1353332 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7513. Min Act: -0.0000

Data Index: 1198713 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.8471. Min Act: -0.0000

Data Index: 657780 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.8402. Min Act: -0.0000

Data Index: 501089 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7042. Min Act: -0.0000

Data Index: 912745 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7013. Min Act: -0.0000

Data Index: 906515 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7682. Min Act: -0.0000

Data Index: 307470 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.6509. Min Act: -0.0000

Data Index: 707051 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7492. Min Act: -0.0000

Data Index: 448249 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.8371. Min Act: -0.0000

Data Index: 703067 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7225. Min Act: -0.0000

Data Index: 100912 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.7042. Min Act: -0.0000

Data Index: 226431 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 2.8673. Min Range: -2.8673

Max Act: 1.5877. Min Act: -0.0000

Data Index: 805938 (C4 (Web Text))

Max Activating Token Index: 486