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

Dataset: The Pile

Neuron 3848 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: 4.4929. Min Range: -4.4929

Max Act: 4.4929. Min Act: -0.0000

Data Index: 1735667 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.8678. Min Act: -0.0000

Data Index: 1523960 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.9993. Min Act: -0.0000

Data Index: 258143 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.9957. Min Act: -0.0000

Data Index: 1297574 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 4.4929. Min Range: -4.4929

Max Act: 4.1621. Min Act: -0.0000

Data Index: 549172 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.4975. Min Act: -0.0000

Data Index: 876083 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.8776. Min Act: -0.0000

Data Index: 29463 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.5586. Min Act: -0.0000

Data Index: 1680568 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.2737. Min Act: -0.0000

Data Index: 1891491 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.5157. Min Act: -0.0000

Data Index: 1573584 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.3481. Min Act: -0.0000

Data Index: 1163159 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.2549. Min Act: -0.0000

Data Index: 619157 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.2187. Min Act: -0.0000

Data Index: 1327484 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.5146. Min Act: -0.0000

Data Index: 95112 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.1692. Min Act: -0.0000

Data Index: 1567092 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.3216. Min Act: -0.0000

Data Index: 1224370 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.1219. Min Act: -0.0000

Data Index: 26503 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.2345. Min Act: -0.0000

Data Index: 440031 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 4.4929. Min Range: -4.4929

Max Act: 3.2073. Min Act: -0.0000

Data Index: 859913 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 4.4929. Min Range: -4.4929

Max Act: 2.8936. Min Act: -0.0000

Data Index: 1008698 (The Pile)

Max Activating Token Index: 681