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

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

Neuron 1478 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1100. Min Range: -2.1100

Max Act: 2.1100. Min Act: -0.0000

Data Index: 9060 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.9101. Min Act: -0.0000

Data Index: 910335 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.8865. Min Act: -0.0000

Data Index: 874595 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1269063 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.8342. Min Act: -0.0000

Data Index: 933211 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1377901 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1165107 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1165947 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6707. Min Act: -0.0000

Data Index: 1297439 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7285. Min Act: -0.0000

Data Index: 145563 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6847. Min Act: -0.0000

Data Index: 784516 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1139424 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7533. Min Act: -0.0000

Data Index: 447619 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1321628 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7440. Min Act: -0.0000

Data Index: 1147478 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7331. Min Act: -0.0000

Data Index: 921803 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.7219. Min Act: -0.0000

Data Index: 645381 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1107662 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1249408 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 2.1100. Min Range: -2.1100

Max Act: 1.6048. Min Act: -0.0000

Data Index: 22072 (C4 (Web Text))

Max Activating Token Index: 256