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

Dataset: The Pile

Neuron 1180 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1140350 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1729146 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1107582 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1323498 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1797874 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0139. Min Act: -0.0000

Data Index: 777921 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0467. Min Act: -0.0000

Data Index: 772636 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0081. Min Act: -0.0000

Data Index: 1956730 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1826916 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0278. Min Act: -0.0000

Data Index: 729520 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0516. Min Act: -0.0000

Data Index: 978210 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1373416 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1641710 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1653249 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1934340 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1027092 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0320. Min Act: -0.0000

Data Index: 360865 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 1.1906. Min Range: -1.1906

Max Act: 1.0347. Min Act: -0.0000

Data Index: 752506 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9923. Min Act: -0.0000

Data Index: 729579 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 1.1906. Min Range: -1.1906

Max Act: 0.9282. Min Act: -0.0000

Data Index: 159385 (The Pile)

Max Activating Token Index: 145