Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2532 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.1944. Min Act: -0.0001

Data Index: 784786 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.1166. Min Act: -0.0001

Data Index: 1178812 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.0613. Min Act: -0.0001

Data Index: 698604 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.0830. Min Act: -0.0001

Data Index: 861923 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.0446. Min Act: -0.0001

Data Index: 923981 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.0930. Min Act: -0.0000

Data Index: 25446 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.0693. Min Act: -0.0000

Data Index: 802180 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.1944. Min Range: -1.1944

Max Act: 1.0341. Min Act: -0.0001

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.9365. Min Act: -0.0001

Data Index: 779922 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.8994. Min Act: -0.0000

Data Index: 280356 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.9437. Min Act: -0.0001

Data Index: 546471 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.8893. Min Act: -0.0000

Data Index: 709657 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.9127. Min Act: -0.0000

Data Index: 640439 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.9342. Min Act: -0.0001

Data Index: 543580 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.8983. Min Act: -0.0001

Data Index: 1158418 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1001847 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.8980. Min Act: -0.0001

Data Index: 509522 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.8492. Min Act: -0.0001

Data Index: 108767 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 1.1944. Min Range: -1.1944

Max Act: 0.8302. Min Act: -0.0001

Data Index: 233164 (C4 (Web Text))

Max Activating Token Index: 612