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

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

Neuron 2240 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: 0.4483. Min Range: -0.4483

Max Act: 0.4346. Min Act: -0.0000

Data Index: 69326 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1518680 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4295. Min Act: -0.0000

Data Index: 314759 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4398. Min Act: -0.0000

Data Index: 727092 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1441803 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1469901 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3993. Min Act: 0.0000

Data Index: 1610248 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1487505 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1523096 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1374433 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3888. Min Act: -0.0000

Data Index: 981292 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1251819 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1641215 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3692. Min Act: -0.0000

Data Index: 800919 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1390656 (Python Code)

Max Activating Token Index: 692

Text #15

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1524723 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1597204 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1645501 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1557237 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1505018 (Python Code)

Max Activating Token Index: 448