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

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

Neuron 2806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.8939. Min Act: -0.0000

Data Index: 139398 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.1486. Min Act: -0.0000

Data Index: 1300704 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.2136. Min Act: -0.0000

Data Index: 484804 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.1795. Min Act: -0.0000

Data Index: 674230 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.7324. Min Act: -0.0000

Data Index: 1377563 (Python Code)

Max Activating Token Index: 476

Text #5

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.4924. Min Act: -0.0000

Data Index: 1502235 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.7473. Min Act: -0.0000

Data Index: 1316954 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.3651. Min Act: -0.0000

Data Index: 732726 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.3956. Min Act: -0.0000

Data Index: 831216 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.3921. Min Act: -0.0000

Data Index: 291082 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 3.8939. Min Range: -3.8939

Max Act: 2.4206. Min Act: -0.0000

Data Index: 522623 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.9654. Min Act: -0.0000

Data Index: 441816 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.8584. Min Act: -0.0000

Data Index: 640489 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.8778. Min Act: -0.0000

Data Index: 1112952 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.9301. Min Act: -0.0000

Data Index: 1098596 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.9350. Min Act: -0.0000

Data Index: 1278880 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.8252. Min Act: -0.0000

Data Index: 915041 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.9090. Min Act: -0.0000

Data Index: 367720 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.9945. Min Act: -0.0000

Data Index: 101107 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 3.8939. Min Range: -3.8939

Max Act: 1.7920. Min Act: -0.0000

Data Index: 582399 (C4 (Web Text))

Max Activating Token Index: 319