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

Dataset: The Pile

Neuron 565 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.9478. Min Act: -0.0000

Data Index: 418074 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 3.1403. Min Range: -3.1403

Max Act: 3.1403. Min Act: -0.0000

Data Index: 36329 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1070574 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7326. Min Act: -0.0000

Data Index: 212520 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.5589. Min Act: -0.0000

Data Index: 474545 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.9638. Min Act: -0.0000

Data Index: 163573 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7819. Min Act: -0.0000

Data Index: 191159 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8556. Min Act: -0.0000

Data Index: 1296956 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7078. Min Act: -0.0000

Data Index: 131172 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.4867. Min Act: -0.0000

Data Index: 1446599 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.6059. Min Act: -0.0000

Data Index: 534529 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.4832. Min Act: -0.0000

Data Index: 1178351 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.5836. Min Act: -0.0000

Data Index: 587111 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.5547. Min Act: -0.0000

Data Index: 773347 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.5485. Min Act: -0.0000

Data Index: 1784007 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.4965. Min Act: -0.0000

Data Index: 1983320 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.6557. Min Act: -0.0000

Data Index: 1214753 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.2542. Min Act: -0.0000

Data Index: 1706376 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.3772. Min Act: -0.0000

Data Index: 532317 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.4998. Min Act: -0.0000

Data Index: 1813601 (The Pile)

Max Activating Token Index: 394