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

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

Neuron 4438 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3523. Min Act: -0.0000

Data Index: 623585 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1082210 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3729. Min Act: -0.0000

Data Index: 903161 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1505621 (Python Code)

Max Activating Token Index: 710

Text #4

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3153. Min Act: -0.0000

Data Index: 501242 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3342. Min Act: -0.0000

Data Index: 621526 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3214. Min Act: -0.0000

Data Index: 473152 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1546861 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1610449 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3259. Min Act: -0.0000

Data Index: 738247 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2867. Min Act: -0.0000

Data Index: 196876 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2792. Min Act: -0.0000

Data Index: 859713 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2946. Min Act: -0.0000

Data Index: 406191 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1168215 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1578100 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1001198 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1138357 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1272755 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1178075 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1147234 (C4 (Web Text))

Max Activating Token Index: 512