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

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

Neuron 4335 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: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1284418 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2923. Min Act: -0.0001

Data Index: 854079 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2506. Min Act: -0.0001

Data Index: 1027332 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1090756 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2408. Min Act: -0.0001

Data Index: 213046 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2661. Min Act: -0.0001

Data Index: 617459 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2472. Min Act: -0.0001

Data Index: 802316 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2608. Min Act: -0.0001

Data Index: 509486 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2211. Min Act: -0.0001

Data Index: 537213 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2036. Min Act: -0.0001

Data Index: 942108 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2152. Min Act: -0.0001

Data Index: 289894 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1239488 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1234146 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1999. Min Act: -0.0001

Data Index: 40838 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1041299 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1936. Min Act: -0.0001

Data Index: 179142 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2078. Min Act: -0.0001

Data Index: 630758 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1800. Min Act: -0.0001

Data Index: 582669 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1781. Min Act: -0.0001

Data Index: 272196 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1989. Min Act: -0.0001

Data Index: 868239 (C4 (Web Text))

Max Activating Token Index: 303