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

Dataset: The Pile

Neuron 1377 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.7117. Min Act: -0.0000

Data Index: 499329 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6795. Min Act: -0.0000

Data Index: 690008 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1404554 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6537. Min Act: -0.0000

Data Index: 1761908 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5555. Min Act: -0.0000

Data Index: 199364 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5238. Min Act: -0.0000

Data Index: 1697239 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1025750 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5774. Min Act: -0.0000

Data Index: 1274563 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6457. Min Act: -0.0000

Data Index: 901162 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5552. Min Act: -0.0000

Data Index: 589333 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1154307 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1935675 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1358682 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4567. Min Act: -0.0000

Data Index: 349352 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1993889 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4949. Min Act: -0.0000

Data Index: 817315 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1535259 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5149. Min Act: -0.0000

Data Index: 403133 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1529304 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1360950 (The Pile)

Max Activating Token Index: 455