Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0124. Min Act: -0.0006

Data Index: 865449 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0113. Min Act: -0.0006

Data Index: 335562 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1069185 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0109. Min Act: -0.0005

Data Index: 624954 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1014935 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0111. Min Act: -0.0006

Data Index: 285115 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1100540 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1552199 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0106. Min Act: -0.0006

Data Index: 403425 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1013259 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1513452 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0105. Min Act: -0.0006

Data Index: 201362 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0102. Min Act: -0.0006

Data Index: 654712 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0106. Min Act: -0.0006

Data Index: 789177 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1200744 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0103. Min Act: -0.0006

Data Index: 167585 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0103. Min Act: -0.0006

Data Index: 779557 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0103. Min Act: -0.0006

Data Index: 451532 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0105. Min Act: -0.0006

Data Index: 27625 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.0124. Min Range: -0.0124

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1306575 (C4 (Web Text))

Max Activating Token Index: 624