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

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

Neuron 2671 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: 4.4651. Min Range: -4.4651

Max Act: 4.3421. Min Act: -0.0000

Data Index: 115604 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 4.4651. Min Range: -4.4651

Max Act: 4.4651. Min Act: -0.0000

Data Index: 384998 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 4.4651. Min Range: -4.4651

Max Act: 4.1799. Min Act: -0.0000

Data Index: 440887 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 4.4651. Min Range: -4.4651

Max Act: 4.0375. Min Act: -0.0000

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 4.4651. Min Range: -4.4651

Max Act: 3.8413. Min Act: -0.0000

Data Index: 896635 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 4.4651. Min Range: -4.4651

Max Act: 4.1079. Min Act: -0.0000

Data Index: 908415 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 4.4651. Min Range: -4.4651

Max Act: 3.5745. Min Act: -0.0000

Data Index: 611826 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 4.4651. Min Range: -4.4651

Max Act: 3.6504. Min Act: -0.0000

Data Index: 1181623 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 4.4651. Min Range: -4.4651

Max Act: 3.4194. Min Act: -0.0000

Data Index: 507956 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 4.4651. Min Range: -4.4651

Max Act: 3.5022. Min Act: -0.0000

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 4.4651. Min Range: -4.4651

Max Act: 3.2356. Min Act: -0.0000

Data Index: 312670 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.8833. Min Act: -0.0000

Data Index: 231630 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.9471. Min Act: -0.0000

Data Index: 230667 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.8492. Min Act: -0.0000

Data Index: 100278 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.8177. Min Act: -0.0000

Data Index: 1276633 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.7403. Min Act: -0.0000

Data Index: 60021 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.7357. Min Act: -0.0000

Data Index: 844501 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.6788. Min Act: -0.0000

Data Index: 66890 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.5080. Min Act: -0.0000

Data Index: 1035664 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 4.4651. Min Range: -4.4651

Max Act: 2.6505. Min Act: -0.0000

Data Index: 116813 (C4 (Web Text))

Max Activating Token Index: 888