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

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

Neuron 322 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0006

Data Index: 110019 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0005

Data Index: 363665 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 131475 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1624445 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0120. Min Act: -0.0006

Data Index: 746717 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1423117 (Python Code)

Max Activating Token Index: 769

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1268580 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0112. Min Act: -0.0006

Data Index: 147259 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 748933 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 456219 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1186038 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1417224 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1148865 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0006

Data Index: 711852 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0110. Min Act: -0.0006

Data Index: 455138 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0006

Data Index: 791775 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0108. Min Act: -0.0006

Data Index: 314264 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0006

Data Index: 398053 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0108. Min Act: -0.0006

Data Index: 703074 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0106. Min Act: -0.0006

Data Index: 750864 (C4 (Web Text))

Max Activating Token Index: 677