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

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

Neuron 28 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.9455. Min Act: -0.0000

Data Index: 614401 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.4354. Min Act: -0.0000

Data Index: 103456 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.0497. Min Act: -0.0000

Data Index: 408089 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.7254. Min Act: -0.0000

Data Index: 40891 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.6836. Min Act: -0.0000

Data Index: 955583 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4514. Min Act: -0.0000

Data Index: 871845 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1063039 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4606. Min Act: -0.0000

Data Index: 1236581 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1346642 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4374. Min Act: -0.0000

Data Index: 409369 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4373. Min Act: -0.0000

Data Index: 413021 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.3388. Min Act: -0.0000

Data Index: 463099 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1182215 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1254057 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.2852. Min Act: -0.0000

Data Index: 789749 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1218686 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.4408. Min Act: -0.0000

Data Index: 85448 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.3688. Min Act: -0.0000

Data Index: 187934 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.3576. Min Act: -0.0000

Data Index: 574329 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 2.9455. Min Range: -2.9455

Max Act: 1.1949. Min Act: -0.0000

Data Index: 477269 (C4 (Web Text))

Max Activating Token Index: 623