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

Dataset: The Pile

Neuron 1128 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: 0.7906. Min Range: -0.7906

Max Act: 0.7512. Min Act: -0.0000

Data Index: 30364 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7645. Min Act: -0.0000

Data Index: 712211 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1723668 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1731387 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1679535 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1489180 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1454251 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7577. Min Act: -0.0000

Data Index: 9109 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7552. Min Act: -0.0000

Data Index: 306390 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1177266 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7661. Min Act: -0.0000

Data Index: 465478 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1020579 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7684. Min Act: -0.0000

Data Index: 553327 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1360361 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6971. Min Act: -0.0000

Data Index: 394858 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7415. Min Act: -0.0000

Data Index: 966988 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7392. Min Act: -0.0000

Data Index: 998509 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6723. Min Act: -0.0000

Data Index: 791220 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7136. Min Act: -0.0000

Data Index: 270811 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1480269 (The Pile)

Max Activating Token Index: 182