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

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

Neuron 4924 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7741. Min Act: -0.0000

Data Index: 906569 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7403. Min Act: 0.0000

Data Index: 666629 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6050. Min Act: -0.0000

Data Index: 530662 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6162. Min Act: -0.0000

Data Index: 47270 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5994. Min Act: -0.0000

Data Index: 481190 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5975. Min Act: -0.0000

Data Index: 999734 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1173421 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5443. Min Act: -0.0000

Data Index: 503242 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1039559 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5349. Min Act: 0.0000

Data Index: 369589 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1104205 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5423. Min Act: -0.0000

Data Index: 639967 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1302312 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5135. Min Act: 0.0000

Data Index: 957668 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1164630 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5151. Min Act: -0.0000

Data Index: 294748 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.4939. Min Act: -0.0000

Data Index: 123992 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.4880. Min Act: -0.0000

Data Index: 336248 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5068. Min Act: -0.0000

Data Index: 718763 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.4877. Min Act: -0.0000

Data Index: 437810 (C4 (Web Text))

Max Activating Token Index: 232