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

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

Neuron 1745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.5539. Min Act: -0.0002

Data Index: 1231308 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4360. Min Act: -0.0002

Data Index: 100474 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4419. Min Act: -0.0002

Data Index: 1285764 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4396. Min Act: -0.0002

Data Index: 456178 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4161. Min Act: -0.0002

Data Index: 817063 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4350. Min Act: -0.0002

Data Index: 276664 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3949. Min Act: -0.0002

Data Index: 854369 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3885. Min Act: -0.0002

Data Index: 278929 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4030. Min Act: -0.0002

Data Index: 36130 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3806. Min Act: -0.0002

Data Index: 999514 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3657. Min Act: -0.0002

Data Index: 909004 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3780. Min Act: -0.0002

Data Index: 211201 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3846. Min Act: -0.0002

Data Index: 1102748 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3773. Min Act: -0.0002

Data Index: 6811 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3454. Min Act: -0.0002

Data Index: 788394 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3744. Min Act: -0.0002

Data Index: 1347282 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3454. Min Act: -0.0002

Data Index: 284671 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3549. Min Act: -0.0002

Data Index: 607853 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3426. Min Act: -0.0002

Data Index: 928256 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.3365. Min Act: -0.0002

Data Index: 146851 (C4 (Web Text))

Max Activating Token Index: 699