Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2056 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0004

Data Index: 47727 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0004

Data Index: 674446 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0152. Min Act: -0.0004

Data Index: 912596 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1369532 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1263223 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0141. Min Act: -0.0004

Data Index: 564540 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1438782 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0140. Min Act: -0.0004

Data Index: 623707 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0144. Min Act: -0.0004

Data Index: 952270 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0144. Min Act: -0.0004

Data Index: 1474569 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1089209 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1494586 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0136. Min Act: -0.0004

Data Index: 719465 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1576854 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0136. Min Act: -0.0004

Data Index: 684071 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0004

Data Index: 287236 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0128. Min Act: -0.0004

Data Index: 1500293 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0004

Data Index: 530362 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0137. Min Act: -0.0004

Data Index: 574587 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0136. Min Act: -0.0004

Data Index: 66142 (C4 (Web Text))

Max Activating Token Index: 763