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

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

Neuron 1605 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: 0.0540. Min Range: -0.0540

Max Act: 0.0501. Min Act: -0.0000

Data Index: 853828 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1273465 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0509. Min Act: -0.0000

Data Index: 929951 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1201528 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0479. Min Act: -0.0000

Data Index: 762333 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1325430 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1240166 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1231043 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0474. Min Act: -0.0000

Data Index: 430329 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0482. Min Act: -0.0000

Data Index: 230181 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1290116 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0481. Min Act: -0.0000

Data Index: 588129 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0468. Min Act: -0.0000

Data Index: 44400 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0373. Min Act: -0.0000

Data Index: 179347 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0422. Min Act: -0.0000

Data Index: 456086 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0427. Min Act: -0.0000

Data Index: 358785 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0456. Min Act: -0.0000

Data Index: 799109 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0430. Min Act: -0.0000

Data Index: 663697 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0506. Min Act: -0.0000

Data Index: 801190 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0440. Min Act: -0.0000

Data Index: 76663 (C4 (Web Text))

Max Activating Token Index: 855