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

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

Neuron 4346 in Layer 0

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: 0.6901. Min Range: -0.6901

Max Act: 0.6901. Min Act: -0.0001

Data Index: 546254 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.6357. Min Act: -0.0001

Data Index: 582077 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.6130. Min Act: -0.0001

Data Index: 323056 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5822. Min Act: -0.0001

Data Index: 893603 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5927. Min Act: -0.0001

Data Index: 1123480 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5880. Min Act: -0.0001

Data Index: 548909 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5798. Min Act: -0.0001

Data Index: 810245 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1124661 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5723. Min Act: -0.0001

Data Index: 809106 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5507. Min Act: -0.0001

Data Index: 885848 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5587. Min Act: -0.0001

Data Index: 275036 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5533. Min Act: -0.0001

Data Index: 249015 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5380. Min Act: -0.0001

Data Index: 128587 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5374. Min Act: -0.0001

Data Index: 154895 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5371. Min Act: -0.0001

Data Index: 553365 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5405. Min Act: -0.0001

Data Index: 364435 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5300. Min Act: -0.0001

Data Index: 452473 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5308. Min Act: -0.0001

Data Index: 145721 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5194. Min Act: -0.0001

Data Index: 1311783 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5256. Min Act: -0.0001

Data Index: 789661 (C4 (Web Text))

Max Activating Token Index: 980