Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1121 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5946. Min Act: -0.0005

Data Index: 1223950 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5978. Min Act: -0.0005

Data Index: 680678 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5945. Min Act: -0.0005

Data Index: 456183 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5588. Min Act: -0.0005

Data Index: 562533 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5702. Min Act: -0.0005

Data Index: 594892 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5695. Min Act: -0.0005

Data Index: 1112906 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5353. Min Act: -0.0005

Data Index: 619459 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5365. Min Act: -0.0005

Data Index: 630811 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5418. Min Act: -0.0005

Data Index: 619697 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5152. Min Act: -0.0005

Data Index: 589204 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5694. Min Act: -0.0005

Data Index: 1135656 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5427. Min Act: -0.0005

Data Index: 76446 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5100. Min Act: -0.0005

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5184. Min Act: -0.0005

Data Index: 538766 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5104. Min Act: -0.0005

Data Index: 1341194 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5265. Min Act: -0.0005

Data Index: 1305532 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5183. Min Act: -0.0005

Data Index: 821338 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5210. Min Act: -0.0005

Data Index: 151503 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5170. Min Act: -0.0005

Data Index: 1313429 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5199. Min Act: -0.0005

Data Index: 151389 (C4 (Web Text))

Max Activating Token Index: 981