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

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

Neuron 3207 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: 0.3259. Min Range: -0.3259

Max Act: 0.3259. Min Act: -0.0001

Data Index: 1155076 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2957. Min Act: -0.0001

Data Index: 536544 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2979. Min Act: -0.0000

Data Index: 673886 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2729. Min Act: -0.0001

Data Index: 403257 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2823. Min Act: -0.0001

Data Index: 869971 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2661. Min Act: -0.0000

Data Index: 358984 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2741. Min Act: -0.0000

Data Index: 498519 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1187456 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2775. Min Act: -0.0001

Data Index: 996419 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2671. Min Act: -0.0000

Data Index: 481102 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2547. Min Act: -0.0001

Data Index: 591075 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1090871 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1312094 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2799. Min Act: -0.0001

Data Index: 1175250 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2536. Min Act: -0.0001

Data Index: 63218 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2487. Min Act: -0.0001

Data Index: 404918 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2469. Min Act: -0.0000

Data Index: 93064 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1291266 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2545. Min Act: -0.0001

Data Index: 440081 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1071093 (C4 (Web Text))

Max Activating Token Index: 158