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

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

Neuron 3430 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0159. Min Range: -1.0159

Max Act: 1.0159. Min Act: -0.0000

Data Index: 1017139 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.0159. Min Range: -1.0159

Max Act: 1.0036. Min Act: -0.0001

Data Index: 1007020 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.9632. Min Act: -0.0000

Data Index: 939930 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.9183. Min Act: -0.0000

Data Index: 56127 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.9057. Min Act: -0.0000

Data Index: 981310 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1064042 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1074008 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1085189 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8951. Min Act: -0.0000

Data Index: 727383 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8477. Min Act: -0.0000

Data Index: 548021 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8364. Min Act: -0.0000

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8138. Min Act: -0.0000

Data Index: 340683 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8604. Min Act: -0.0001

Data Index: 765215 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8518. Min Act: -0.0001

Data Index: 308289 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8436. Min Act: -0.0000

Data Index: 19976 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8547. Min Act: -0.0000

Data Index: 686847 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8179. Min Act: -0.0000

Data Index: 930457 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8087. Min Act: -0.0001

Data Index: 792892 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7847. Min Act: -0.0000

Data Index: 264585 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7852. Min Act: -0.0000

Data Index: 913067 (C4 (Web Text))

Max Activating Token Index: 750