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

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

Neuron 5502 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.3951. Min Act: -0.0000

Data Index: 176103 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.8647. Min Act: -0.0000

Data Index: 266012 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.7438. Min Act: -0.0000

Data Index: 597089 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.5034. Min Act: -0.0000

Data Index: 680594 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.2618. Min Act: -0.0000

Data Index: 220185 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.4598. Min Act: -0.0000

Data Index: 369625 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.5778. Min Act: -0.0000

Data Index: 1020323 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 3.3951. Min Range: -3.3951

Max Act: 1.9298. Min Act: -0.0000

Data Index: 572762 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.3080. Min Act: -0.0000

Data Index: 1250316 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.1317. Min Act: -0.0000

Data Index: 935770 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.3031. Min Act: -0.0000

Data Index: 767408 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.1159. Min Act: -0.0000

Data Index: 363257 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.1618. Min Act: -0.0000

Data Index: 93274 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.0279. Min Act: -0.0000

Data Index: 356653 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 3.3951. Min Range: -3.3951

Max Act: 1.9267. Min Act: -0.0000

Data Index: 1169362 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 3.3951. Min Range: -3.3951

Max Act: 1.9255. Min Act: -0.0000

Data Index: 499111 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.0260. Min Act: -0.0000

Data Index: 966790 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 3.3951. Min Range: -3.3951

Max Act: 1.8637. Min Act: -0.0000

Data Index: 848028 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 3.3951. Min Range: -3.3951

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1248474 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 3.3951. Min Range: -3.3951

Max Act: 1.7507. Min Act: -0.0000

Data Index: 114202 (C4 (Web Text))

Max Activating Token Index: 637