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

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

Neuron 3237 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0646. Min Act: -0.0001

Data Index: 476244 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0880. Min Act: -0.0001

Data Index: 977644 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0527. Min Act: -0.0001

Data Index: 797525 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0159. Min Act: -0.0001

Data Index: 409707 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9385. Min Act: -0.0001

Data Index: 824721 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9048. Min Act: -0.0001

Data Index: 436451 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0154. Min Act: -0.0001

Data Index: 141691 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0673. Min Act: -0.0001

Data Index: 529916 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1121111 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0400. Min Act: -0.0001

Data Index: 13487 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8809. Min Act: -0.0001

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0606. Min Act: -0.0001

Data Index: 461298 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9910. Min Act: -0.0001

Data Index: 808779 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0007. Min Act: -0.0001

Data Index: 480378 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0507. Min Act: -0.0001

Data Index: 471381 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9595. Min Act: -0.0001

Data Index: 696866 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9549. Min Act: -0.0001

Data Index: 272392 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9890. Min Act: -0.0001

Data Index: 1314743 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9837. Min Act: -0.0001

Data Index: 505421 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9815. Min Act: -0.0001

Data Index: 734361 (C4 (Web Text))

Max Activating Token Index: 608