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

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

Neuron 3705 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: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1638629 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1635661 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1525902 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1504586 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1564721 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1530666 (Python Code)

Max Activating Token Index: 126

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1530088 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1536965 (Python Code)

Max Activating Token Index: 427

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1363728 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1488363 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1620871 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1552407 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1578478 (Python Code)

Max Activating Token Index: 810

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1364150 (Python Code)

Max Activating Token Index: 226

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1631092 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1650115 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1505022 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1361259 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2993. Min Act: -0.0000

Data Index: 552373 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1396857 (Python Code)

Max Activating Token Index: 680