Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2947 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.7456. Min Act: -0.0000

Data Index: 851328 (The Pile)

Max Activating Token Index: 987

Text #1

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3071. Min Act: -0.0000

Data Index: 1723816 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.5038. Min Act: -0.0000

Data Index: 1998872 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.2929. Min Act: -0.0000

Data Index: 1521631 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3694. Min Act: -0.0000

Data Index: 1973572 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.9912. Min Act: -0.0000

Data Index: 816511 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.9682. Min Act: -0.0000

Data Index: 1764664 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.1025. Min Act: -0.0000

Data Index: 1982421 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.0583. Min Act: -0.0000

Data Index: 867264 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.9040. Min Act: -0.0000

Data Index: 851492 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.8822. Min Act: -0.0000

Data Index: 1581477 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.9100. Min Act: -0.0000

Data Index: 1230824 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.0098. Min Act: -0.0000

Data Index: 1417186 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.8719. Min Act: -0.0000

Data Index: 1898937 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.9663. Min Act: -0.0000

Data Index: 773011 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.7806. Min Act: -0.0000

Data Index: 143627 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.9192. Min Act: -0.0000

Data Index: 1893925 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.6050. Min Act: -0.0000

Data Index: 497542 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.5864. Min Act: -0.0000

Data Index: 1296125 (The Pile)

Max Activating Token Index: 502

Text #19

Max Range: 3.7456. Min Range: -3.7456

Max Act: 2.5890. Min Act: -0.0000

Data Index: 1383839 (The Pile)

Max Activating Token Index: 236