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

Dataset: The Pile

Neuron 3136 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: 0.3842. Min Range: -0.3842

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1322376 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3486. Min Act: -0.0000

Data Index: 114809 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3277. Min Act: -0.0000

Data Index: 160791 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1050665 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1145318 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1985938 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3127. Min Act: -0.0000

Data Index: 932543 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3183. Min Act: -0.0000

Data Index: 451408 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1013455 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1536365 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3119. Min Act: -0.0000

Data Index: 137367 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1849016 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1859709 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2868. Min Act: -0.0000

Data Index: 731824 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1064326 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1416515 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1062140 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3163. Min Act: -0.0000

Data Index: 893568 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3079. Min Act: -0.0000

Data Index: 947430 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2930. Min Act: -0.0000

Data Index: 270190 (The Pile)

Max Activating Token Index: 98