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

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

Neuron 1442 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.8027. Min Act: -0.0000

Data Index: 925632 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5582. Min Act: -0.0000

Data Index: 752052 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5514. Min Act: 0.0000

Data Index: 324902 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4896. Min Act: 0.0000

Data Index: 300751 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4862. Min Act: -0.0000

Data Index: 179764 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4805. Min Act: 0.0000

Data Index: 295620 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4906. Min Act: 0.0000

Data Index: 330166 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4599. Min Act: 0.0001

Data Index: 430781 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1518540 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4124. Min Act: -0.0000

Data Index: 973799 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4041. Min Act: -0.0000

Data Index: 983446 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4389. Min Act: -0.0000

Data Index: 307238 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1417384 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4174. Min Act: 0.0000

Data Index: 977110 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4077. Min Act: -0.0000

Data Index: 281440 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1650899 (Python Code)

Max Activating Token Index: 419

Text #16

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.4066. Min Act: 0.0001

Data Index: 1175426 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1173835 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.3987. Min Act: 0.0000

Data Index: 705906 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.3637. Min Act: -0.0000

Data Index: 266393 (C4 (Web Text))

Max Activating Token Index: 107