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

Dataset: The Pile

Neuron 774 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: 0.6435. Min Range: -0.6435

Max Act: 0.6422. Min Act: -0.0000

Data Index: 802108 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.6435. Min Act: -0.0000

Data Index: 708090 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1202699 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5470. Min Act: -0.0000

Data Index: 948458 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1750296 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1168603 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1935415 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1141720 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5500. Min Act: -0.0000

Data Index: 531351 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1428938 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1955503 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5205. Min Act: -0.0000

Data Index: 178325 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1977596 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1935777 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4819. Min Act: -0.0000

Data Index: 536074 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4867. Min Act: -0.0000

Data Index: 787104 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4742. Min Act: -0.0000

Data Index: 284139 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1877668 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1204007 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.6435. Min Range: -0.6435

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1308529 (The Pile)

Max Activating Token Index: 342