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

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

Neuron 5876 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3637. Min Range: -3.3637

Max Act: 3.3637. Min Act: -0.0000

Data Index: 283486 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.3637. Min Range: -3.3637

Max Act: 2.8240. Min Act: -0.0000

Data Index: 1002476 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 3.3637. Min Range: -3.3637

Max Act: 3.0801. Min Act: -0.0000

Data Index: 705541 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.3637. Min Range: -3.3637

Max Act: 2.6046. Min Act: -0.0000

Data Index: 1233138 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 3.3637. Min Range: -3.3637

Max Act: 2.3369. Min Act: -0.0000

Data Index: 927041 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 3.3637. Min Range: -3.3637

Max Act: 2.1570. Min Act: -0.0000

Data Index: 882464 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 3.3637. Min Range: -3.3637

Max Act: 2.1465. Min Act: -0.0000

Data Index: 1256675 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.9842. Min Act: -0.0000

Data Index: 954705 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.8810. Min Act: -0.0000

Data Index: 636663 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.8039. Min Act: -0.0000

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.7356. Min Act: -0.0000

Data Index: 609714 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.6809. Min Act: -0.0000

Data Index: 690335 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.7208. Min Act: -0.0000

Data Index: 258848 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1234819 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1195141 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.5131. Min Act: -0.0000

Data Index: 186070 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.4728. Min Act: -0.0000

Data Index: 438991 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.5181. Min Act: -0.0000

Data Index: 616148 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.5432. Min Act: -0.0000

Data Index: 919894 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.3637. Min Range: -3.3637

Max Act: 1.4064. Min Act: -0.0000

Data Index: 1309713 (C4 (Web Text))

Max Activating Token Index: 327