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

Dataset: The Pile

Neuron 3810 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1343766 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1152. Min Act: -0.0000

Data Index: 571787 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1100. Min Act: -0.0000

Data Index: 502847 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1183. Min Act: -0.0000

Data Index: 835455 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1085. Min Act: -0.0000

Data Index: 499264 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1382798 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1032. Min Act: -0.0000

Data Index: 552489 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1230064 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0990. Min Act: -0.0000

Data Index: 426617 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1710941 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1754684 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0951. Min Act: -0.0000

Data Index: 13178 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1785602 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1208639 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0925. Min Act: -0.0000

Data Index: 215577 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1924170 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1956135 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1399019 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1053. Min Act: -0.0000

Data Index: 325373 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0956. Min Act: -0.0000

Data Index: 436938 (The Pile)

Max Activating Token Index: 526