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

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

Neuron 2870 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3837. Min Act: -0.0000

Data Index: 625513 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3129. Min Act: -0.0000

Data Index: 858902 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3886. Min Act: -0.0000

Data Index: 966662 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3323. Min Act: -0.0000

Data Index: 218481 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3095. Min Act: -0.0000

Data Index: 22587 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3157. Min Act: -0.0000

Data Index: 595478 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2711. Min Act: -0.0000

Data Index: 872288 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3095. Min Act: -0.0000

Data Index: 785655 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2515. Min Act: -0.0000

Data Index: 727309 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1055100 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2793. Min Act: -0.0000

Data Index: 298209 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2524. Min Act: -0.0000

Data Index: 952806 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2489. Min Act: -0.0000

Data Index: 435722 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2412. Min Act: -0.0000

Data Index: 529117 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2559. Min Act: -0.0000

Data Index: 906380 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2396. Min Act: -0.0000

Data Index: 483652 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2437. Min Act: -0.0000

Data Index: 498009 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2142. Min Act: -0.0000

Data Index: 56717 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2225. Min Act: -0.0001

Data Index: 108723 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2354. Min Act: -0.0001

Data Index: 744768 (C4 (Web Text))

Max Activating Token Index: 684