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

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

Neuron 3907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0414. Min Range: -2.0414

Max Act: 2.0414. Min Act: -0.0000

Data Index: 630545 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.8098. Min Act: -0.0000

Data Index: 385381 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.8331. Min Act: -0.0000

Data Index: 909969 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6819. Min Act: -0.0000

Data Index: 377877 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.8743. Min Act: -0.0000

Data Index: 810976 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.7615. Min Act: -0.0000

Data Index: 105407 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6962. Min Act: -0.0000

Data Index: 606312 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6661. Min Act: -0.0000

Data Index: 42371 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.7126. Min Act: -0.0000

Data Index: 917279 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6802. Min Act: -0.0000

Data Index: 592348 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1024292 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.5659. Min Act: -0.0000

Data Index: 81800 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.5671. Min Act: -0.0000

Data Index: 905400 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1163506 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.5574. Min Act: -0.0000

Data Index: 1015967 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6780. Min Act: -0.0000

Data Index: 699802 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.4540. Min Act: -0.0000

Data Index: 255742 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.5662. Min Act: -0.0000

Data Index: 185647 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.6617. Min Act: -0.0000

Data Index: 254948 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 2.0414. Min Range: -2.0414

Max Act: 1.4734. Min Act: -0.0000

Data Index: 373163 (C4 (Web Text))

Max Activating Token Index: 165