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

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

Neuron 319 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: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0003

Data Index: 402711 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0638. Min Act: -0.0002

Data Index: 858398 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0599. Min Act: -0.0002

Data Index: 333672 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0505. Min Act: -0.0002

Data Index: 355587 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0475. Min Act: -0.0002

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0415. Min Act: -0.0002

Data Index: 458035 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1287527 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0398. Min Act: -0.0002

Data Index: 68932 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0384. Min Act: -0.0003

Data Index: 683269 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0377. Min Act: -0.0002

Data Index: 596944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0372. Min Act: -0.0002

Data Index: 421818 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0372. Min Act: -0.0002

Data Index: 630460 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0366. Min Act: -0.0002

Data Index: 162052 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0366. Min Act: -0.0002

Data Index: 595111 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1322331 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1032177 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0363. Min Act: -0.0002

Data Index: 895293 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0344. Min Act: -0.0002

Data Index: 267533 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0348. Min Act: -0.0002

Data Index: 357873 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0356. Min Act: -0.0002

Data Index: 947532 (C4 (Web Text))

Max Activating Token Index: 226