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

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

Neuron 3894 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.4501. Min Act: -0.0000

Data Index: 712186 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.0591. Min Act: -0.0000

Data Index: 433632 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 2.4501. Min Range: -2.4501

Max Act: 2.0171. Min Act: -0.0000

Data Index: 681527 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8258. Min Act: -0.0000

Data Index: 322343 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8970. Min Act: -0.0000

Data Index: 509081 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.9787. Min Act: -0.0000

Data Index: 541519 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8568. Min Act: -0.0000

Data Index: 806780 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8358. Min Act: -0.0000

Data Index: 868064 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8206. Min Act: -0.0000

Data Index: 930327 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.7893. Min Act: -0.0000

Data Index: 54246 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8535. Min Act: -0.0000

Data Index: 810615 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.6549. Min Act: -0.0000

Data Index: 81189 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.8262. Min Act: -0.0000

Data Index: 920206 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.7283. Min Act: -0.0000

Data Index: 484523 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1113760 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.6104. Min Act: -0.0000

Data Index: 25409 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.6285. Min Act: -0.0000

Data Index: 951720 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.6035. Min Act: -0.0000

Data Index: 989878 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.5928. Min Act: -0.0000

Data Index: 4814 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 2.4501. Min Range: -2.4501

Max Act: 1.7583. Min Act: -0.0000

Data Index: 7838 (C4 (Web Text))

Max Activating Token Index: 235