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

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

Neuron 928 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: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0006

Data Index: 241745 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1224154 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0153. Min Act: -0.0006

Data Index: 370763 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1206658 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0150. Min Act: -0.0006

Data Index: 43417 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0150. Min Act: -0.0006

Data Index: 914736 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1172781 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1234085 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0149. Min Act: -0.0006

Data Index: 191137 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0148. Min Act: -0.0006

Data Index: 514003 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0148. Min Act: -0.0006

Data Index: 519129 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0006

Data Index: 43386 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0006

Data Index: 712521 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0146. Min Act: -0.0006

Data Index: 2423 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0006

Data Index: 757898 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0141. Min Act: -0.0006

Data Index: 736966 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0147. Min Act: -0.0006

Data Index: 400595 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0143. Min Act: -0.0006

Data Index: 90921 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0143. Min Act: -0.0006

Data Index: 65268 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0140. Min Act: -0.0006

Data Index: 924397 (C4 (Web Text))

Max Activating Token Index: 23