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

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

Neuron 3632 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.8526. Min Act: -0.0000

Data Index: 660120 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.7965. Min Act: -0.0000

Data Index: 438661 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6615. Min Act: -0.0000

Data Index: 536934 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6835. Min Act: -0.0000

Data Index: 786537 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6593. Min Act: -0.0000

Data Index: 543242 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1322180 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6060. Min Act: -0.0000

Data Index: 986232 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6120. Min Act: -0.0000

Data Index: 983965 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6225. Min Act: -0.0000

Data Index: 968209 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6221. Min Act: -0.0000

Data Index: 74518 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6456. Min Act: -0.0000

Data Index: 461724 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.6425. Min Act: 0.0000

Data Index: 821972 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1309475 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5327. Min Act: -0.0000

Data Index: 784588 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1140402 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1224125 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5948. Min Act: -0.0000

Data Index: 990454 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5729. Min Act: -0.0000

Data Index: 431126 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5763. Min Act: 0.0000

Data Index: 290758 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.8526. Min Range: -0.8526

Max Act: 0.5566. Min Act: -0.0000

Data Index: 650520 (C4 (Web Text))

Max Activating Token Index: 386