Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 672 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0159. Min Act: -0.0006

Data Index: 645389 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0006

Data Index: 176560 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0006

Data Index: 424495 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0006

Data Index: 131492 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0142. Min Act: -0.0006

Data Index: 348651 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0141. Min Act: -0.0006

Data Index: 410864 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0136. Min Act: -0.0006

Data Index: 376510 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0138. Min Act: -0.0006

Data Index: 759957 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0138. Min Act: -0.0006

Data Index: 986751 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1124175 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1322198 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0130. Min Act: -0.0006

Data Index: 220069 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1183099 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1348615 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0135. Min Act: -0.0006

Data Index: 374079 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0131. Min Act: -0.0006

Data Index: 44306 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0131. Min Act: -0.0006

Data Index: 317641 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0128. Min Act: -0.0006

Data Index: 943218 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0130. Min Act: -0.0006

Data Index: 18064 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0130. Min Act: -0.0006

Data Index: 640880 (C4 (Web Text))

Max Activating Token Index: 461