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

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

Neuron 5904 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5717. Min Range: -5.5717

Max Act: 5.5717. Min Act: -0.0000

Data Index: 649608 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 5.5717. Min Range: -5.5717

Max Act: 5.4079. Min Act: -0.0000

Data Index: 733457 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 5.5717. Min Range: -5.5717

Max Act: 5.0186. Min Act: -0.0000

Data Index: 707222 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 5.5717. Min Range: -5.5717

Max Act: 5.3281. Min Act: -0.0000

Data Index: 250636 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.8743. Min Act: -0.0000

Data Index: 792522 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 5.5717. Min Range: -5.5717

Max Act: 5.1704. Min Act: -0.0000

Data Index: 356609 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.5717. Min Range: -5.5717

Max Act: 5.1043. Min Act: -0.0000

Data Index: 950576 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.5385. Min Act: -0.0000

Data Index: 588074 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.8485. Min Act: -0.0000

Data Index: 1200978 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.4770. Min Act: -0.0000

Data Index: 239952 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.7312. Min Act: -0.0000

Data Index: 814610 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.3273. Min Act: -0.0000

Data Index: 255707 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.0645. Min Act: -0.0000

Data Index: 520715 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.4128. Min Act: 0.0000

Data Index: 492628 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.3998. Min Act: 0.0000

Data Index: 590720 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.3539. Min Act: -0.0000

Data Index: 791479 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.0048. Min Act: -0.0000

Data Index: 794509 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.5048. Min Act: -0.0000

Data Index: 974095 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.2638. Min Act: -0.0000

Data Index: 721599 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 5.5717. Min Range: -5.5717

Max Act: 4.1949. Min Act: -0.0000

Data Index: 963688 (C4 (Web Text))

Max Activating Token Index: 431