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

Dataset: The Pile

Neuron 2892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1758575 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5920. Min Act: -0.0000

Data Index: 828216 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5462. Min Act: -0.0000

Data Index: 128650 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1465936 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1677711 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5313. Min Act: -0.0000

Data Index: 869641 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1921528 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1379740 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5055. Min Act: -0.0000

Data Index: 817782 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1860909 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1381633 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4983. Min Act: -0.0000

Data Index: 929029 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5214. Min Act: -0.0000

Data Index: 909939 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5039. Min Act: -0.0000

Data Index: 591641 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1344105 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1132550 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1710763 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1882935 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1944296 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4937. Min Act: -0.0000

Data Index: 555914 (The Pile)

Max Activating Token Index: 254