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

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

Neuron 4747 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3661. Min Range: -5.3661

Max Act: 5.3661. Min Act: -0.0000

Data Index: 1209236 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 5.3661. Min Range: -5.3661

Max Act: 5.0053. Min Act: -0.0000

Data Index: 580204 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.7651. Min Act: -0.0000

Data Index: 1516337 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.3933. Min Act: -0.0000

Data Index: 1257104 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.4073. Min Act: -0.0000

Data Index: 1551715 (Python Code)

Max Activating Token Index: 645

Text #5

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.6703. Min Act: -0.0000

Data Index: 1045535 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.3305. Min Act: -0.0000

Data Index: 109063 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.6243. Min Act: -0.0000

Data Index: 724246 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.3735. Min Act: -0.0000

Data Index: 700271 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.8895. Min Act: -0.0000

Data Index: 251817 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 5.3661. Min Range: -5.3661

Max Act: 3.8917. Min Act: -0.0000

Data Index: 293020 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.5117. Min Act: -0.0000

Data Index: 1298360 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.0347. Min Act: -0.0000

Data Index: 1452979 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.3545. Min Act: -0.0000

Data Index: 892667 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.2974. Min Act: -0.0000

Data Index: 506190 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.2922. Min Act: -0.0000

Data Index: 1030387 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.2667. Min Act: -0.0001

Data Index: 906439 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 5.3661. Min Range: -5.3661

Max Act: 3.5854. Min Act: -0.0000

Data Index: 1640361 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 5.3661. Min Range: -5.3661

Max Act: 4.0239. Min Act: -0.0000

Data Index: 694536 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 5.3661. Min Range: -5.3661

Max Act: 3.8556. Min Act: -0.0001

Data Index: 214221 (C4 (Web Text))

Max Activating Token Index: 884