Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4212 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0552. Min Range: -1.0552

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1273732 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1599631 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1498368 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1446704 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1451124 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1355233 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1551184 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1523009 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3140. Min Act: -0.0000

Data Index: 488481 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1449570 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3026. Min Act: -0.0000

Data Index: 333815 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1079224 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.3049. Min Act: -0.0000

Data Index: 162768 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.2861. Min Act: -0.0000

Data Index: 91652 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.2780. Min Act: -0.0000

Data Index: 173225 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.2914. Min Act: -0.0000

Data Index: 995050 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.2601. Min Act: -0.0000

Data Index: 190370 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.0552. Min Range: -1.0552

Max Act: 0.2822. Min Act: -0.0000

Data Index: 843888 (C4 (Web Text))

Max Activating Token Index: 68