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

Dataset: The Pile

Neuron 2377 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.2423. Min Act: -0.0000

Data Index: 168687 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.2337. Min Act: -0.0000

Data Index: 1760028 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6960. Min Act: -0.0000

Data Index: 1027500 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.0715. Min Act: -0.0000

Data Index: 962585 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.8124. Min Act: -0.0000

Data Index: 365145 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.5641. Min Act: -0.0000

Data Index: 1405827 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.8050. Min Act: -0.0000

Data Index: 1844259 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.7785. Min Act: -0.0000

Data Index: 1231273 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.6731. Min Act: -0.0000

Data Index: 176943 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.5488. Min Act: -0.0000

Data Index: 380414 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.6218. Min Act: -0.0000

Data Index: 455281 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.6544. Min Act: -0.0000

Data Index: 257489 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.3790. Min Act: -0.0000

Data Index: 33605 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.4640. Min Act: -0.0000

Data Index: 146856 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.4497. Min Act: -0.0000

Data Index: 624194 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.3532. Min Act: -0.0000

Data Index: 1706308 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.3695. Min Act: -0.0000

Data Index: 974736 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.2869. Min Act: -0.0000

Data Index: 1609041 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.2636. Min Act: -0.0000

Data Index: 1192223 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 3.6960. Min Range: -3.6960

Max Act: 2.2417. Min Act: -0.0000

Data Index: 1752583 (The Pile)

Max Activating Token Index: 170