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

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

Neuron 2696 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: 1.2466. Min Range: -1.2466

Max Act: 1.2466. Min Act: -0.0002

Data Index: 918732 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.2098. Min Act: -0.0002

Data Index: 322124 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1912. Min Act: -0.0002

Data Index: 1323882 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1628. Min Act: -0.0002

Data Index: 600364 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1447. Min Act: -0.0002

Data Index: 1311000 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1414. Min Act: -0.0002

Data Index: 139351 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1160. Min Act: -0.0002

Data Index: 977271 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0880. Min Act: -0.0002

Data Index: 943577 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1147. Min Act: -0.0002

Data Index: 842303 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1040. Min Act: -0.0002

Data Index: 846008 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0759. Min Act: -0.0002

Data Index: 1340212 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0956. Min Act: -0.0002

Data Index: 570137 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0892. Min Act: -0.0002

Data Index: 715823 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1514838 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1591045 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1496410 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1421879 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1495791 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1574575 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0723. Min Act: -0.0002

Data Index: 129241 (C4 (Web Text))

Max Activating Token Index: 1