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

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

Neuron 167 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0921. Min Range: -4.0921

Max Act: 4.0921. Min Act: -0.0000

Data Index: 1106449 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.9926. Min Act: -0.0000

Data Index: 117173 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.9208. Min Act: -0.0000

Data Index: 1316472 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.0031. Min Act: -0.0000

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 4.0921. Min Range: -4.0921

Max Act: 3.1604. Min Act: -0.0000

Data Index: 1262049 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.9616. Min Act: -0.0000

Data Index: 930006 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.7193. Min Act: -0.0000

Data Index: 890543 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.8547. Min Act: -0.0000

Data Index: 833027 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.9939. Min Act: -0.0000

Data Index: 161235 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.7864. Min Act: -0.0000

Data Index: 1222550 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.6058. Min Act: -0.0000

Data Index: 64224 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.7338. Min Act: -0.0000

Data Index: 815549 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.6559. Min Act: -0.0000

Data Index: 1494824 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.7888. Min Act: -0.0000

Data Index: 511077 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.6556. Min Act: -0.0000

Data Index: 1485094 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.6059. Min Act: -0.0000

Data Index: 525555 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.3305. Min Act: -0.0000

Data Index: 1372751 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.5733. Min Act: -0.0000

Data Index: 893895 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.4346. Min Act: -0.0000

Data Index: 1361858 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 4.0921. Min Range: -4.0921

Max Act: 2.6717. Min Act: -0.0000

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 670