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

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

Neuron 400 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.9880. Min Act: -0.0000

Data Index: 534208 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.6660. Min Act: -0.0000

Data Index: 78397 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.6737. Min Act: -0.0000

Data Index: 1224004 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.6812. Min Act: -0.0000

Data Index: 450391 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.5446. Min Act: -0.0000

Data Index: 73241 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.7905. Min Act: -0.0000

Data Index: 1182788 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.7034. Min Act: -0.0000

Data Index: 1263567 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.4251. Min Act: -0.0000

Data Index: 901174 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.3585. Min Act: -0.0000

Data Index: 1020636 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1206879 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.4238. Min Act: -0.0000

Data Index: 723638 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.2937. Min Act: -0.0000

Data Index: 121419 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.5396. Min Act: -0.0000

Data Index: 915122 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.5354. Min Act: -0.0000

Data Index: 848047 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.4115. Min Act: -0.0000

Data Index: 253737 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.2660. Min Act: -0.0000

Data Index: 488133 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.3626. Min Act: -0.0000

Data Index: 684646 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.2309. Min Act: -0.0000

Data Index: 57329 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.1099. Min Act: -0.0000

Data Index: 120130 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.9880. Min Range: -2.9880

Max Act: 2.1674. Min Act: -0.0000

Data Index: 633573 (C4 (Web Text))

Max Activating Token Index: 482