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

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

Neuron 2572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.7796. Min Act: -0.0000

Data Index: 650743 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.7184. Min Act: -0.0000

Data Index: 147923 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.2744. Min Act: -0.0000

Data Index: 320219 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.6297. Min Act: -0.0000

Data Index: 407734 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.5979. Min Act: -0.0000

Data Index: 660010 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.5790. Min Act: -0.0000

Data Index: 573987 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.7115. Min Act: -0.0000

Data Index: 1017662 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.2981. Min Act: -0.0000

Data Index: 1219485 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.8054. Min Act: -0.0000

Data Index: 278158 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 6.7796. Min Range: -6.7796

Max Act: 6.1943. Min Act: -0.0000

Data Index: 1248922 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.7763. Min Act: -0.0000

Data Index: 474599 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.5849. Min Act: -0.0000

Data Index: 1066525 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.8117. Min Act: -0.0000

Data Index: 314135 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.5090. Min Act: -0.0000

Data Index: 710162 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.7221. Min Act: -0.0000

Data Index: 208141 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.6045. Min Act: -0.0000

Data Index: 1251054 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.8174. Min Act: -0.0000

Data Index: 516873 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.6043. Min Act: -0.0000

Data Index: 520530 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.3938. Min Act: -0.0000

Data Index: 556337 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 6.7796. Min Range: -6.7796

Max Act: 5.5203. Min Act: -0.0000

Data Index: 808398 (C4 (Web Text))

Max Activating Token Index: 555