Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2644 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.6561. Min Act: -0.0001

Data Index: 1222456 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.6123. Min Act: -0.0001

Data Index: 799513 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5820. Min Act: -0.0001

Data Index: 456461 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1239579 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5433. Min Act: -0.0001

Data Index: 569219 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5073. Min Act: -0.0001

Data Index: 988614 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5429. Min Act: -0.0001

Data Index: 225777 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4911. Min Act: -0.0001

Data Index: 275630 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4431. Min Act: -0.0001

Data Index: 296611 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5107. Min Act: -0.0001

Data Index: 344928 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4525. Min Act: -0.0001

Data Index: 1122001 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4830. Min Act: -0.0001

Data Index: 1115380 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5030. Min Act: -0.0001

Data Index: 1001236 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4790. Min Act: -0.0001

Data Index: 269658 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5330. Min Act: -0.0001

Data Index: 71955 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4758. Min Act: -0.0001

Data Index: 441127 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4771. Min Act: -0.0001

Data Index: 261187 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4743. Min Act: -0.0001

Data Index: 586797 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4680. Min Act: -0.0001

Data Index: 113951 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4816. Min Act: -0.0001

Data Index: 330225 (C4 (Web Text))

Max Activating Token Index: 862