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

Dataset: The Pile

Neuron 133 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: 0.2595. Min Range: -0.2595

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1864918 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2516. Min Act: -0.0000

Data Index: 625056 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2568. Min Act: -0.0000

Data Index: 848866 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2405. Min Act: -0.0000

Data Index: 4082 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1609183 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2445. Min Act: -0.0000

Data Index: 427461 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1062206 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2123. Min Act: -0.0000

Data Index: 661654 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2106. Min Act: -0.0000

Data Index: 250946 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2118. Min Act: -0.0000

Data Index: 794598 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1301686 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1808271 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2242. Min Act: -0.0000

Data Index: 339176 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1214428 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1106904 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1554106 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2091. Min Act: -0.0000

Data Index: 964078 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2081. Min Act: -0.0000

Data Index: 329811 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1084502 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1934. Min Act: -0.0000

Data Index: 11838 (The Pile)

Max Activating Token Index: 354