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

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

Neuron 2374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0183. Min Act: -0.0001

Data Index: 493743 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1083722 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1432782 (Python Code)

Max Activating Token Index: 933

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1272886 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1545135 (Python Code)

Max Activating Token Index: 418

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1445376 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0134. Min Act: -0.0000

Data Index: 1428653 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0131. Min Act: -0.0001

Data Index: 585349 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1331590 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0130. Min Act: -0.0001

Data Index: 275959 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1544652 (Python Code)

Max Activating Token Index: 830

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1274283 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1639128 (Python Code)

Max Activating Token Index: 539

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0130. Min Act: -0.0000

Data Index: 1374929 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1582008 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0129. Min Act: -0.0001

Data Index: 718264 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1416560 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0121. Min Act: -0.0001

Data Index: 987566 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1293773 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0122. Min Act: -0.0001

Data Index: 916622 (C4 (Web Text))

Max Activating Token Index: 576