Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 525 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1189971 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.7350. Min Act: -0.0000

Data Index: 886915 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1356887 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6731. Min Act: -0.0000

Data Index: 549608 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6442. Min Act: -0.0000

Data Index: 225920 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6504. Min Act: -0.0000

Data Index: 354999 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.7085. Min Act: -0.0000

Data Index: 840900 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.7022. Min Act: -0.0000

Data Index: 587914 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6615. Min Act: -0.0000

Data Index: 617768 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6453. Min Act: -0.0000

Data Index: 361142 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.7240. Min Act: -0.0000

Data Index: 139410 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1140739 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6296. Min Act: -0.0000

Data Index: 329989 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6764. Min Act: -0.0000

Data Index: 225665 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6206. Min Act: -0.0000

Data Index: 316300 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6218. Min Act: -0.0000

Data Index: 602374 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6406. Min Act: -0.0000

Data Index: 709628 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1096877 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.6139. Min Act: -0.0000

Data Index: 832710 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.8818. Min Range: -0.8818

Max Act: 0.5063. Min Act: -0.0000

Data Index: 309475 (C4 (Web Text))

Max Activating Token Index: 285