Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2095 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2907. Min Act: -0.0001

Data Index: 365150 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2776. Min Act: -0.0001

Data Index: 892441 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2483. Min Act: -0.0001

Data Index: 89108 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2666. Min Act: -0.0001

Data Index: 275994 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1564210 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2457. Min Act: -0.0001

Data Index: 462022 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2512. Min Act: -0.0001

Data Index: 1458631 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2446. Min Act: -0.0001

Data Index: 235638 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1469904 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2443. Min Act: -0.0001

Data Index: 1149715 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2391. Min Act: -0.0001

Data Index: 741843 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1255986 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2310. Min Act: -0.0001

Data Index: 781454 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2453. Min Act: -0.0001

Data Index: 52075 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2436. Min Act: -0.0001

Data Index: 858078 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2496. Min Act: -0.0001

Data Index: 740092 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2610. Min Act: -0.0001

Data Index: 269644 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2479. Min Act: -0.0001

Data Index: 746468 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2478. Min Act: -0.0001

Data Index: 879619 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.2907. Min Range: -0.2907

Max Act: 0.2340. Min Act: -0.0001

Data Index: 148252 (C4 (Web Text))

Max Activating Token Index: 462