Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3481. Min Act: -0.0001

Data Index: 1571442 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0001

Data Index: 761039 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3441. Min Act: -0.0001

Data Index: 993026 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3387. Min Act: 0.0002

Data Index: 193094 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3387. Min Act: -0.0001

Data Index: 613803 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3507. Min Act: -0.0001

Data Index: 1121423 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1123595 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3465. Min Act: -0.0001

Data Index: 326383 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3483. Min Act: -0.0001

Data Index: 67052 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3341. Min Act: -0.0001

Data Index: 206505 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3112. Min Act: -0.0001

Data Index: 240194 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3204. Min Act: -0.0000

Data Index: 534815 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2942. Min Act: -0.0001

Data Index: 4553 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3565. Min Act: -0.0001

Data Index: 87052 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3154. Min Act: -0.0001

Data Index: 441489 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3043. Min Act: -0.0001

Data Index: 830692 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3084. Min Act: -0.0001

Data Index: 821714 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3091. Min Act: -0.0001

Data Index: 593467 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3165. Min Act: -0.0001

Data Index: 905668 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1000813 (C4 (Web Text))

Max Activating Token Index: 82