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

Dataset: The Pile

Neuron 2843 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1046036 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4653. Min Act: -0.0000

Data Index: 892574 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4622. Min Act: -0.0000

Data Index: 367946 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4570. Min Act: -0.0000

Data Index: 567541 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1506689 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1071454 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4661. Min Act: -0.0000

Data Index: 483229 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1269597 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4072. Min Act: -0.0000

Data Index: 958979 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4115. Min Act: -0.0000

Data Index: 465375 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1079584 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4110. Min Act: -0.0000

Data Index: 292401 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1147607 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1883122 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1434377 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3542. Min Act: -0.0000

Data Index: 699839 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1104488 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1978489 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3927. Min Act: -0.0000

Data Index: 833864 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1464557 (The Pile)

Max Activating Token Index: 959