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

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

Neuron 1979 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0003

Data Index: 13883 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0522. Min Act: -0.0002

Data Index: 49932 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0523. Min Act: -0.0003

Data Index: 137634 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0496. Min Act: -0.0003

Data Index: 472807 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0483. Min Act: -0.0003

Data Index: 58582 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0480. Min Act: -0.0003

Data Index: 954350 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0470. Min Act: -0.0003

Data Index: 389635 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1001229 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0465. Min Act: -0.0003

Data Index: 434298 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0462. Min Act: -0.0003

Data Index: 574219 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0440. Min Act: -0.0003

Data Index: 799705 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0440. Min Act: -0.0003

Data Index: 589451 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0440. Min Act: -0.0003

Data Index: 193946 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0427. Min Act: -0.0003

Data Index: 856122 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1105109 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0440. Min Act: -0.0003

Data Index: 403240 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1045857 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0430. Min Act: -0.0003

Data Index: 6927 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0428. Min Act: -0.0003

Data Index: 157383 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0420. Min Act: -0.0003

Data Index: 652708 (C4 (Web Text))

Max Activating Token Index: 186