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

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

Neuron 3439 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1157. Min Range: -1.1157

Max Act: 1.1157. Min Act: -0.0000

Data Index: 836524 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.1157. Min Range: -1.1157

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1163378 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9498. Min Act: -0.0000

Data Index: 741848 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9734. Min Act: -0.0000

Data Index: 711804 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9374. Min Act: -0.0000

Data Index: 864854 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9826. Min Act: -0.0000

Data Index: 298817 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9176. Min Act: -0.0000

Data Index: 465212 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9122. Min Act: -0.0000

Data Index: 146654 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9320. Min Act: -0.0000

Data Index: 71263 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9732. Min Act: -0.0000

Data Index: 33110 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8811. Min Act: -0.0000

Data Index: 445726 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1212522 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8333. Min Act: -0.0000

Data Index: 16755 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7588. Min Act: -0.0000

Data Index: 239138 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1265557 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7802. Min Act: -0.0000

Data Index: 971091 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8119. Min Act: -0.0000

Data Index: 356828 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7380. Min Act: -0.0000

Data Index: 13 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7625. Min Act: -0.0000

Data Index: 936371 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7583. Min Act: -0.0000

Data Index: 817987 (C4 (Web Text))

Max Activating Token Index: 290