Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1521031 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1608266 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1398853 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1295. Min Act: -0.0000

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1547583 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1547251 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1372927 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1538267 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1595612 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1533439 (Python Code)

Max Activating Token Index: 685

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1428694 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1049. Min Act: -0.0000

Data Index: 754361 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1537619 (Python Code)

Max Activating Token Index: 632

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1547081 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1649445 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1556283 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1593138 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1635734 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1453490 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1559121 (Python Code)

Max Activating Token Index: 264