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

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

Neuron 4001 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1231642 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0113. Min Act: -0.0003

Data Index: 966554 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0107. Min Act: -0.0003

Data Index: 291259 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0109. Min Act: -0.0003

Data Index: 518749 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0092. Min Act: -0.0003

Data Index: 486861 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0093. Min Act: -0.0003

Data Index: 924542 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0093. Min Act: -0.0003

Data Index: 218243 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0091. Min Act: -0.0002

Data Index: 114383 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0087. Min Act: -0.0003

Data Index: 804718 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0089. Min Act: -0.0003

Data Index: 465702 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1261901 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0088. Min Act: -0.0002

Data Index: 7364 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0087. Min Act: -0.0002

Data Index: 463880 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0087. Min Act: -0.0002

Data Index: 979462 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0087. Min Act: -0.0002

Data Index: 960127 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0086. Min Act: -0.0003

Data Index: 446879 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0085. Min Act: -0.0003

Data Index: 38284 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0085. Min Act: -0.0002

Data Index: 835258 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1242851 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0084. Min Act: -0.0003

Data Index: 975641 (C4 (Web Text))

Max Activating Token Index: 560