Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 150 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.6091. Min Act: -0.0001

Data Index: 426567 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1055505 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5420. Min Act: -0.0001

Data Index: 450902 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4657. Min Act: -0.0000

Data Index: 829029 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4929. Min Act: -0.0000

Data Index: 125094 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4838. Min Act: -0.0001

Data Index: 399153 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4828. Min Act: -0.0000

Data Index: 232659 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4587. Min Act: -0.0001

Data Index: 1032139 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4424. Min Act: -0.0000

Data Index: 76138 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1215446 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4658. Min Act: -0.0001

Data Index: 1025723 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4471. Min Act: -0.0000

Data Index: 347721 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1342087 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1036039 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4414. Min Act: -0.0001

Data Index: 648324 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1278396 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4478. Min Act: -0.0001

Data Index: 756057 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4335. Min Act: -0.0001

Data Index: 108046 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4287. Min Act: -0.0000

Data Index: 548059 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4296. Min Act: -0.0000

Data Index: 9061 (C4 (Web Text))

Max Activating Token Index: 378