Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2618 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0002

Data Index: 928232 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0152. Min Act: -0.0002

Data Index: 824749 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1225048 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0002

Data Index: 201465 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0143. Min Act: -0.0002

Data Index: 530214 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1090148 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1167647 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0002

Data Index: 97203 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0002

Data Index: 507632 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0002

Data Index: 902269 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0002

Data Index: 127955 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1129845 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0002

Data Index: 228687 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0002

Data Index: 913502 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1209978 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0002

Data Index: 272993 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1117245 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0002

Data Index: 286173 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0002

Data Index: 295319 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0002

Data Index: 848237 (C4 (Web Text))

Max Activating Token Index: 656