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

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

Neuron 1525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.6491. Min Act: -0.0001

Data Index: 1286291 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.5252. Min Act: -0.0001

Data Index: 331246 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3676. Min Act: -0.0001

Data Index: 914045 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4844. Min Act: -0.0001

Data Index: 366143 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4526. Min Act: -0.0001

Data Index: 1002851 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4327. Min Act: -0.0001

Data Index: 944959 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4252. Min Act: -0.0001

Data Index: 81955 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4248. Min Act: -0.0001

Data Index: 511572 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3844. Min Act: -0.0001

Data Index: 178635 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1214408 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.4217. Min Act: -0.0001

Data Index: 757119 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3726. Min Act: -0.0001

Data Index: 935932 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3990. Min Act: -0.0001

Data Index: 9546 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.2837. Min Act: -0.0001

Data Index: 941560 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3695. Min Act: -0.0001

Data Index: 910368 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3809. Min Act: -0.0001

Data Index: 710510 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3540. Min Act: -0.0001

Data Index: 1043081 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1146638 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3361. Min Act: -0.0001

Data Index: 12647 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.6491. Min Range: -0.6491

Max Act: 0.3612. Min Act: -0.0001

Data Index: 1008390 (C4 (Web Text))

Max Activating Token Index: 695