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

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

Neuron 4614 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 338056 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0164. Min Act: -0.0002

Data Index: 811167 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1239430 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1634566 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0159. Min Act: -0.0002

Data Index: 113424 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0162. Min Act: -0.0002

Data Index: 762633 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1274502 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1151930 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0002

Data Index: 752438 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0138. Min Act: -0.0002

Data Index: 410661 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1518784 (Python Code)

Max Activating Token Index: 692

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1589318 (Python Code)

Max Activating Token Index: 489

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0132. Min Act: -0.0002

Data Index: 782736 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0131. Min Act: -0.0002

Data Index: 898978 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0137. Min Act: -0.0002

Data Index: 388173 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1611204 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0147. Min Act: -0.0002

Data Index: 207168 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1337696 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1560570 (Python Code)

Max Activating Token Index: 641

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1511221 (Python Code)

Max Activating Token Index: 68