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

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

Neuron 2739 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1543804 (Python Code)

Max Activating Token Index: 784

Text #1

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.6574. Min Act: -0.0001

Data Index: 859011 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7040. Min Act: -0.0001

Data Index: 387687 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.6800. Min Act: -0.0001

Data Index: 79687 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5258. Min Act: -0.0001

Data Index: 748050 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.6957. Min Act: -0.0001

Data Index: 765138 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.4243. Min Act: -0.0001

Data Index: 180160 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1462328 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5178. Min Act: -0.0001

Data Index: 1385963 (Python Code)

Max Activating Token Index: 831

Text #9

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.4503. Min Act: -0.0001

Data Index: 80302 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5219. Min Act: -0.0001

Data Index: 1569287 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5267. Min Act: -0.0001

Data Index: 789993 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5233. Min Act: -0.0001

Data Index: 124017 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5044. Min Act: -0.0001

Data Index: 81743 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.4568. Min Act: -0.0001

Data Index: 143780 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5915. Min Act: -0.0001

Data Index: 1014993 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1434214 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.5365. Min Act: -0.0001

Data Index: 880768 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.4365. Min Act: -0.0001

Data Index: 30411 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1404321 (Python Code)

Max Activating Token Index: 493