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

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

Neuron 689 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6992. Min Range: -5.6992

Max Act: 5.6992. Min Act: -0.0000

Data Index: 1043672 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.7420. Min Act: -0.0000

Data Index: 24127 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.5061. Min Act: -0.0000

Data Index: 1121658 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.6268. Min Act: -0.0000

Data Index: 190578 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.4973. Min Act: -0.0000

Data Index: 1220657 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.5885. Min Act: -0.0000

Data Index: 1074876 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.2943. Min Act: -0.0000

Data Index: 1120056 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.1200. Min Act: -0.0000

Data Index: 865494 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.2530. Min Act: -0.0000

Data Index: 683219 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 5.6992. Min Range: -5.6992

Max Act: 4.0282. Min Act: -0.0000

Data Index: 690128 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.7560. Min Act: -0.0000

Data Index: 785208 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.8516. Min Act: -0.0000

Data Index: 3270 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.7347. Min Act: -0.0000

Data Index: 77982 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.7422. Min Act: -0.0000

Data Index: 571168 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.7162. Min Act: -0.0000

Data Index: 242168 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.8160. Min Act: -0.0000

Data Index: 323784 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.6384. Min Act: -0.0000

Data Index: 782405 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.8189. Min Act: -0.0000

Data Index: 400665 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.7573. Min Act: -0.0000

Data Index: 1199456 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 5.6992. Min Range: -5.6992

Max Act: 3.5957. Min Act: -0.0000

Data Index: 527801 (C4 (Web Text))

Max Activating Token Index: 86