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

Dataset: The Pile

Neuron 2035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1935531 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3344. Min Act: -0.0000

Data Index: 933685 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3294. Min Act: -0.0000

Data Index: 828399 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1566860 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1722726 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1064453 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3256. Min Act: -0.0000

Data Index: 720926 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3231. Min Act: -0.0000

Data Index: 270024 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3087. Min Act: -0.0000

Data Index: 345898 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3121. Min Act: -0.0000

Data Index: 357499 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1471465 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3139. Min Act: -0.0000

Data Index: 64552 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3052. Min Act: -0.0000

Data Index: 540262 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1804139 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1141149 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1063675 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.2979. Min Act: -0.0000

Data Index: 839747 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3003. Min Act: -0.0000

Data Index: 806282 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1595856 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3034. Min Act: -0.0000

Data Index: 929542 (The Pile)

Max Activating Token Index: 142