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

Dataset: The Pile

Neuron 4882 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: 5.2937. Min Range: -5.2937

Max Act: 5.1320. Min Act: -0.0000

Data Index: 85276 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 5.2937. Min Range: -5.2937

Max Act: 5.2937. Min Act: -0.0000

Data Index: 1547014 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.4126. Min Act: -0.0000

Data Index: 288561 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.3410. Min Act: -0.0000

Data Index: 1911667 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.1551. Min Act: -0.0000

Data Index: 853 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.9998. Min Act: -0.0000

Data Index: 248379 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.1082. Min Act: -0.0000

Data Index: 1983321 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.9151. Min Act: -0.0000

Data Index: 1926330 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.9065. Min Act: -0.0000

Data Index: 13945 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.9089. Min Act: -0.0000

Data Index: 146098 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.8312. Min Act: -0.0000

Data Index: 1331108 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.7436. Min Act: -0.0000

Data Index: 1990882 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.4325. Min Act: -0.0000

Data Index: 1148246 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 5.2937. Min Range: -5.2937

Max Act: 4.0260. Min Act: -0.0000

Data Index: 442550 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.5822. Min Act: -0.0000

Data Index: 1858606 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.6155. Min Act: -0.0000

Data Index: 1139347 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.7625. Min Act: -0.0000

Data Index: 207675 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.4116. Min Act: -0.0000

Data Index: 126717 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.5521. Min Act: -0.0000

Data Index: 1079202 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 5.2937. Min Range: -5.2937

Max Act: 3.8750. Min Act: -0.0000

Data Index: 1838135 (The Pile)

Max Activating Token Index: 505