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

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

Neuron 621 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: 0.0147. Min Range: -0.0147

Max Act: 0.0147. Min Act: -0.0006

Data Index: 635055 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0142. Min Act: -0.0006

Data Index: 612260 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0140. Min Act: -0.0006

Data Index: 876503 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0136. Min Act: -0.0006

Data Index: 571496 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0134. Min Act: -0.0006

Data Index: 988170 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0137. Min Act: -0.0006

Data Index: 230769 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0140. Min Act: -0.0006

Data Index: 522074 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0134. Min Act: -0.0006

Data Index: 640440 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0136. Min Act: -0.0006

Data Index: 281019 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0136. Min Act: -0.0006

Data Index: 149636 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0138. Min Act: -0.0006

Data Index: 502817 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1353680 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1342422 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0137. Min Act: -0.0006

Data Index: 912284 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0134. Min Act: -0.0006

Data Index: 22737 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1100724 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0132. Min Act: -0.0006

Data Index: 189061 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1135843 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1140195 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0128. Min Act: -0.0006

Data Index: 368613 (C4 (Web Text))

Max Activating Token Index: 388