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

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

Neuron 345 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1006503 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1244937 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0749. Min Act: -0.0000

Data Index: 440472 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0643. Min Act: -0.0000

Data Index: 77645 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0591. Min Act: -0.0000

Data Index: 165923 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1018812 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0503. Min Act: -0.0000

Data Index: 244137 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1053538 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1652134 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1265119 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0505. Min Act: -0.0000

Data Index: 188415 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0524. Min Act: -0.0000

Data Index: 411927 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0517. Min Act: -0.0000

Data Index: 49792 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0507. Min Act: -0.0000

Data Index: 958349 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1027554 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0493. Min Act: -0.0000

Data Index: 227138 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1178484 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0485. Min Act: -0.0000

Data Index: 937722 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0481. Min Act: -0.0000

Data Index: 338505 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0931. Min Range: -0.0931

Max Act: 0.0479. Min Act: -0.0000

Data Index: 437257 (C4 (Web Text))

Max Activating Token Index: 437