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

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

Neuron 231 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: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1279789 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0164. Min Act: -0.0006

Data Index: 37395 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0141. Min Act: -0.0006

Data Index: 622731 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0136. Min Act: -0.0006

Data Index: 119567 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0141. Min Act: -0.0006

Data Index: 443387 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0136. Min Act: -0.0006

Data Index: 450070 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1266767 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0138. Min Act: -0.0006

Data Index: 57782 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1161364 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0130. Min Act: -0.0006

Data Index: 484567 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0131. Min Act: -0.0006

Data Index: 69346 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0124. Min Act: -0.0006

Data Index: 361970 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0127. Min Act: -0.0006

Data Index: 593351 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0128. Min Act: -0.0006

Data Index: 912092 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0130. Min Act: -0.0006

Data Index: 6601 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0121. Min Act: -0.0006

Data Index: 45238 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0124. Min Act: -0.0006

Data Index: 486372 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0121. Min Act: -0.0006

Data Index: 133984 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0126. Min Act: -0.0006

Data Index: 872267 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0119. Min Act: -0.0006

Data Index: 558247 (C4 (Web Text))

Max Activating Token Index: 41