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

Dataset: The Pile

Neuron 2167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1335880 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1544108 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7417. Min Act: -0.0000

Data Index: 914309 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6501. Min Act: -0.0000

Data Index: 568892 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1241902 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1338777 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1371092 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1471040 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5449. Min Act: -0.0000

Data Index: 537678 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4996. Min Act: -0.0000

Data Index: 24425 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5010. Min Act: -0.0000

Data Index: 765492 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5073. Min Act: -0.0000

Data Index: 41626 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4308. Min Act: -0.0000

Data Index: 37890 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1886243 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1413736 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1507193 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4129. Min Act: -0.0000

Data Index: 179427 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.5038. Min Act: -0.0000

Data Index: 412740 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1100450 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.4815. Min Act: -0.0000

Data Index: 885974 (The Pile)

Max Activating Token Index: 705