Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1297 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0594. Min Act: -0.0006

Data Index: 1525536 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0006

Data Index: 950510 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0492. Min Act: -0.0006

Data Index: 1488837 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0492. Min Act: -0.0006

Data Index: 1633275 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0484. Min Act: -0.0006

Data Index: 643452 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0489. Min Act: -0.0006

Data Index: 359574 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1613576 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1631235 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1634925 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1400250 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1397524 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0412. Min Act: -0.0006

Data Index: 297586 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0434. Min Act: -0.0006

Data Index: 1521065 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0419. Min Act: -0.0006

Data Index: 180341 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0444. Min Act: -0.0006

Data Index: 1437737 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1361442 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1493159 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0432. Min Act: -0.0006

Data Index: 1410873 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0450. Min Act: -0.0006

Data Index: 1490719 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0325. Min Act: -0.0006

Data Index: 176060 (C4 (Web Text))

Max Activating Token Index: 996