Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3987 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0958. Min Range: -3.0958

Max Act: 3.0958. Min Act: -0.0001

Data Index: 901056 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.4074. Min Act: -0.0001

Data Index: 582928 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1380. Min Act: -0.0001

Data Index: 1120533 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.2606. Min Act: -0.0001

Data Index: 183193 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1207. Min Act: -0.0001

Data Index: 1043820 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.3352. Min Act: -0.0001

Data Index: 244650 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1074. Min Act: -0.0001

Data Index: 1295270 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1856. Min Act: -0.0001

Data Index: 475426 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1491. Min Act: -0.0001

Data Index: 1078521 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1616. Min Act: -0.0001

Data Index: 201960 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.0276. Min Act: -0.0001

Data Index: 707620 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.1138. Min Act: -0.0001

Data Index: 1034220 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 3.0958. Min Range: -3.0958

Max Act: 2.0119. Min Act: -0.0001

Data Index: 1184723 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.9567. Min Act: -0.0001

Data Index: 895701 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.8599. Min Act: -0.0001

Data Index: 557171 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.8396. Min Act: -0.0001

Data Index: 299073 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.9212. Min Act: -0.0001

Data Index: 8095 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.9033. Min Act: -0.0001

Data Index: 1081515 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.7996. Min Act: -0.0001

Data Index: 618695 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.0958. Min Range: -3.0958

Max Act: 1.9031. Min Act: -0.0001

Data Index: 238723 (C4 (Web Text))

Max Activating Token Index: 384