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

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

Neuron 1761 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4435. Min Act: -0.0005

Data Index: 22588 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3673. Min Act: -0.0005

Data Index: 452461 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3684. Min Act: -0.0005

Data Index: 914474 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3694. Min Act: -0.0005

Data Index: 581226 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3467. Min Act: -0.0005

Data Index: 878810 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3443. Min Act: -0.0005

Data Index: 733734 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3330. Min Act: -0.0005

Data Index: 90040 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3394. Min Act: -0.0005

Data Index: 949600 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3298. Min Act: -0.0005

Data Index: 205487 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3416. Min Act: -0.0005

Data Index: 982257 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3448. Min Act: -0.0005

Data Index: 1262946 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3419. Min Act: -0.0005

Data Index: 1305577 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3467. Min Act: -0.0005

Data Index: 304816 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3393. Min Act: -0.0005

Data Index: 1069221 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3592. Min Act: -0.0005

Data Index: 1209050 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3471. Min Act: -0.0005

Data Index: 1145682 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3583. Min Act: -0.0005

Data Index: 1321200 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3469. Min Act: -0.0005

Data Index: 793038 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3303. Min Act: -0.0005

Data Index: 28794 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3497. Min Act: -0.0005

Data Index: 1103936 (C4 (Web Text))

Max Activating Token Index: 635