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

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

Neuron 265 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8339. Min Act: -0.0001

Data Index: 106653 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8718. Min Act: -0.0001

Data Index: 1118745 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6504. Min Act: -0.0001

Data Index: 893434 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7523. Min Act: -0.0001

Data Index: 882050 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.5703. Min Act: -0.0001

Data Index: 130582 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6963. Min Act: -0.0001

Data Index: 1344370 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6938. Min Act: -0.0001

Data Index: 1240369 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6743. Min Act: -0.0001

Data Index: 1314273 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8480. Min Act: -0.0001

Data Index: 945979 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.4831. Min Act: -0.0001

Data Index: 1276328 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.4889. Min Act: -0.0001

Data Index: 305042 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8035. Min Act: -0.0001

Data Index: 1035591 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.6123. Min Act: -0.0001

Data Index: 1161271 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.5827. Min Act: -0.0001

Data Index: 1084551 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7276. Min Act: -0.0001

Data Index: 1282181 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.5575. Min Act: -0.0001

Data Index: 634156 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.4127. Min Act: -0.0001

Data Index: 1022674 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.5159. Min Act: -0.0001

Data Index: 18649 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.5166. Min Act: -0.0001

Data Index: 180087 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.4589. Min Act: -0.0001

Data Index: 1078840 (C4 (Web Text))

Max Activating Token Index: 799