Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 117 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1234977 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1221709 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0172. Min Act: -0.0001

Data Index: 756629 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0001

Data Index: 926377 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0001

Data Index: 617486 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0001

Data Index: 382749 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0001

Data Index: 770309 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0001

Data Index: 443905 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1060575 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0001

Data Index: 190257 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0001

Data Index: 321986 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1053039 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0001

Data Index: 448324 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0001

Data Index: 831414 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1184673 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0001

Data Index: 224536 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0001

Data Index: 785678 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1170276 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1107592 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1170268 (C4 (Web Text))

Max Activating Token Index: 763