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

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

Neuron 694 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6134. Min Range: -3.6134

Max Act: 3.6134. Min Act: -0.0001

Data Index: 1170247 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.9637. Min Act: -0.0001

Data Index: 1320426 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.9001. Min Act: -0.0001

Data Index: 368601 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.4047. Min Act: -0.0001

Data Index: 1013865 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2662. Min Act: -0.0000

Data Index: 16710 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2787. Min Act: -0.0000

Data Index: 407283 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.3600. Min Act: -0.0001

Data Index: 613592 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.3212. Min Act: -0.0001

Data Index: 695063 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2065. Min Act: -0.0001

Data Index: 1007386 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2554. Min Act: -0.0001

Data Index: 1088382 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2338. Min Act: -0.0001

Data Index: 396844 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.4637. Min Act: -0.0001

Data Index: 360264 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2205. Min Act: -0.0000

Data Index: 533521 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.3290. Min Act: -0.0001

Data Index: 280203 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.2138. Min Act: -0.0001

Data Index: 306590 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.3177. Min Act: -0.0000

Data Index: 879042 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.3071. Min Act: -0.0001

Data Index: 639075 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.0087. Min Act: -0.0001

Data Index: 177751 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.0929. Min Act: -0.0000

Data Index: 1143223 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 3.6134. Min Range: -3.6134

Max Act: 2.0767. Min Act: -0.0001

Data Index: 627202 (C4 (Web Text))

Max Activating Token Index: 116