Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2655 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0003

Data Index: 89591 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0534. Min Act: -0.0003

Data Index: 374128 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1250567 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1280528 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1171211 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0499. Min Act: -0.0003

Data Index: 599284 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1196927 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1274800 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0431. Min Act: -0.0003

Data Index: 394080 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0462. Min Act: -0.0003

Data Index: 329707 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1002298 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1285170 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0452. Min Act: -0.0003

Data Index: 626425 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0437. Min Act: -0.0003

Data Index: 103193 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0423. Min Act: -0.0003

Data Index: 697948 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0413. Min Act: -0.0003

Data Index: 820913 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0409. Min Act: -0.0003

Data Index: 112986 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0406. Min Act: -0.0003

Data Index: 690071 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0434. Min Act: -0.0003

Data Index: 61981 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0408. Min Act: -0.0003

Data Index: 558975 (C4 (Web Text))

Max Activating Token Index: 191