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

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

Neuron 5485 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3825. Min Range: -4.3825

Max Act: 4.2731. Min Act: -0.0001

Data Index: 213945 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 4.3825. Min Range: -4.3825

Max Act: 4.3825. Min Act: -0.0001

Data Index: 379201 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.6977. Min Act: -0.0001

Data Index: 603965 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.8800. Min Act: -0.0001

Data Index: 598405 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.3720. Min Act: -0.0001

Data Index: 1020956 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.6219. Min Act: -0.0001

Data Index: 759713 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.2929. Min Act: -0.0001

Data Index: 957088 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.2962. Min Act: -0.0001

Data Index: 1020159 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.2858. Min Act: -0.0001

Data Index: 443433 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.4247. Min Act: -0.0001

Data Index: 818693 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.4107. Min Act: -0.0000

Data Index: 462044 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.4685. Min Act: -0.0000

Data Index: 752051 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.0089. Min Act: -0.0000

Data Index: 732260 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.3989. Min Act: -0.0001

Data Index: 144085 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 4.3825. Min Range: -4.3825

Max Act: 2.9637. Min Act: -0.0001

Data Index: 298249 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.1297. Min Act: -0.0000

Data Index: 1279763 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.1143. Min Act: -0.0000

Data Index: 294629 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.0882. Min Act: -0.0001

Data Index: 181780 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.2227. Min Act: -0.0001

Data Index: 198256 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 4.3825. Min Range: -4.3825

Max Act: 3.0548. Min Act: -0.0000

Data Index: 631936 (C4 (Web Text))

Max Activating Token Index: 77