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

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

Neuron 388 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5884. Min Act: -0.0001

Data Index: 458559 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.6071. Min Act: -0.0001

Data Index: 710070 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5699. Min Act: -0.0001

Data Index: 637725 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.6030. Min Act: -0.0001

Data Index: 240225 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4823. Min Act: -0.0001

Data Index: 114980 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5570. Min Act: -0.0001

Data Index: 360544 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5464. Min Act: -0.0001

Data Index: 83099 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4820. Min Act: -0.0001

Data Index: 649565 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5496. Min Act: -0.0001

Data Index: 1349666 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4876. Min Act: -0.0001

Data Index: 932621 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5098. Min Act: -0.0001

Data Index: 574522 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4598. Min Act: -0.0001

Data Index: 1061535 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4462. Min Act: -0.0001

Data Index: 746478 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1276295 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5399. Min Act: -0.0001

Data Index: 412456 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4918. Min Act: -0.0001

Data Index: 1321632 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4335. Min Act: -0.0001

Data Index: 315006 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.5297. Min Act: -0.0001

Data Index: 1072868 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4491. Min Act: -0.0001

Data Index: 362641 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.6071. Min Range: -0.6071

Max Act: 0.4444. Min Act: -0.0001

Data Index: 233567 (C4 (Web Text))

Max Activating Token Index: 110