Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1934 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0105. Min Act: -0.0006

Data Index: 405826 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0102. Min Act: -0.0006

Data Index: 249778 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0098. Min Act: -0.0006

Data Index: 557061 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0091. Min Act: -0.0006

Data Index: 482849 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1146305 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1071926 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 216417 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 600968 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 741717 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0093. Min Act: -0.0006

Data Index: 828218 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 673416 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 566552 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 923366 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0087. Min Act: -0.0006

Data Index: 667958 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 802361 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0087. Min Act: -0.0006

Data Index: 609085 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 678407 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 840633 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 496359 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 721288 (C4 (Web Text))

Max Activating Token Index: 729