Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2022 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1308621 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.4279. Min Act: -0.0000

Data Index: 644394 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3843. Min Act: -0.0000

Data Index: 479986 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3541. Min Act: -0.0000

Data Index: 147788 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3612. Min Act: -0.0000

Data Index: 74286 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3541. Min Act: -0.0000

Data Index: 285746 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1321746 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1265163 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3349. Min Act: -0.0000

Data Index: 31913 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1032719 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3130. Min Act: -0.0000

Data Index: 660579 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3117. Min Act: -0.0000

Data Index: 624804 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3213. Min Act: -0.0000

Data Index: 108889 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3112. Min Act: -0.0000

Data Index: 214915 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2930. Min Act: -0.0000

Data Index: 854956 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2970. Min Act: -0.0000

Data Index: 134582 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.3116. Min Act: -0.0000

Data Index: 57230 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2832. Min Act: -0.0000

Data Index: 508261 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1248036 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.4510. Min Range: -0.4510

Max Act: 0.2903. Min Act: -0.0000

Data Index: 998684 (C4 (Web Text))

Max Activating Token Index: 151