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

Dataset: The Pile

Neuron 2660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2937. Min Act: -0.0000

Data Index: 159702 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2489. Min Act: -0.0000

Data Index: 746193 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1140867 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2348. Min Act: -0.0000

Data Index: 832143 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2261. Min Act: -0.0000

Data Index: 206517 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1082169 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2210. Min Act: -0.0000

Data Index: 892949 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2148. Min Act: -0.0000

Data Index: 699758 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2219. Min Act: -0.0000

Data Index: 558220 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1796053 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1169631 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2043. Min Act: -0.0000

Data Index: 992400 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1262466 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1081918 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2096. Min Act: -0.0000

Data Index: 832461 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1954. Min Act: -0.0000

Data Index: 470328 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1955119 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2145. Min Act: -0.0000

Data Index: 300058 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1442059 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2040. Min Act: -0.0000

Data Index: 549409 (The Pile)

Max Activating Token Index: 797