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

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

Neuron 3174 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.4027. Min Act: -0.0000

Data Index: 921465 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3734. Min Act: -0.0000

Data Index: 19571 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3859. Min Act: -0.0000

Data Index: 405584 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3729. Min Act: -0.0000

Data Index: 978241 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3313. Min Act: 0.0000

Data Index: 1174303 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3585. Min Act: -0.0000

Data Index: 935 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1346934 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3086. Min Act: -0.0000

Data Index: 265394 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3265. Min Act: -0.0000

Data Index: 597045 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3258. Min Act: -0.0000

Data Index: 741912 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1314556 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2940. Min Act: -0.0000

Data Index: 845859 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2956. Min Act: -0.0000

Data Index: 523786 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2940. Min Act: -0.0000

Data Index: 170389 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2919. Min Act: -0.0000

Data Index: 603197 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1093628 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2874. Min Act: -0.0000

Data Index: 98063 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2886. Min Act: -0.0000

Data Index: 832990 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2939. Min Act: -0.0000

Data Index: 737063 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2930. Min Act: -0.0000

Data Index: 567052 (C4 (Web Text))

Max Activating Token Index: 483