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

Dataset: The Pile

Neuron 1776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.9888. Min Act: -0.0000

Data Index: 851930 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.7213. Min Act: -0.0000

Data Index: 1298214 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.5913. Min Act: -0.0000

Data Index: 523405 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.8500. Min Act: -0.0000

Data Index: 227869 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.6193. Min Act: -0.0000

Data Index: 423039 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.9174. Min Act: -0.0000

Data Index: 1104915 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.5883. Min Act: -0.0000

Data Index: 885229 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.7414. Min Act: -0.0000

Data Index: 1735107 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.8595. Min Act: -0.0000

Data Index: 1347321 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.5272. Min Act: -0.0000

Data Index: 1546416 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.3134. Min Act: -0.0000

Data Index: 1813563 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.7748. Min Act: -0.0000

Data Index: 929212 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.7857. Min Act: -0.0000

Data Index: 1124935 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.4761. Min Act: -0.0000

Data Index: 1305584 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.8098. Min Act: -0.0000

Data Index: 1024892 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.4564. Min Act: -0.0000

Data Index: 1610866 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.4196. Min Act: -0.0000

Data Index: 105706 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.4304. Min Act: -0.0000

Data Index: 1040859 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.5939. Min Act: -0.0000

Data Index: 1591355 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 3.9888. Min Range: -3.9888

Max Act: 3.6931. Min Act: -0.0000

Data Index: 1521908 (The Pile)

Max Activating Token Index: 541