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

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

Neuron 4184 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4102. Min Range: -5.4102

Max Act: 5.4102. Min Act: -0.0000

Data Index: 217931 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 5.4102. Min Range: -5.4102

Max Act: 4.7552. Min Act: -0.0000

Data Index: 1064983 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 5.4102. Min Range: -5.4102

Max Act: 4.1901. Min Act: -0.0000

Data Index: 1151683 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 5.4102. Min Range: -5.4102

Max Act: 4.1128. Min Act: -0.0000

Data Index: 1110906 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 5.4102. Min Range: -5.4102

Max Act: 4.2274. Min Act: -0.0000

Data Index: 1079033 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.7563. Min Act: 0.0001

Data Index: 1374535 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.9461. Min Act: -0.0000

Data Index: 505435 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.7031. Min Act: -0.0000

Data Index: 405488 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.4072. Min Act: -0.0000

Data Index: 557560 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.7908. Min Act: -0.0000

Data Index: 1321161 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.7918. Min Act: -0.0000

Data Index: 993123 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.8688. Min Act: -0.0000

Data Index: 1171144 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.6233. Min Act: 0.0001

Data Index: 1455530 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.5873. Min Act: -0.0000

Data Index: 246161 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.4671. Min Act: -0.0000

Data Index: 274277 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.4560. Min Act: -0.0000

Data Index: 1644315 (Python Code)

Max Activating Token Index: 79

Text #16

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.2669. Min Act: -0.0000

Data Index: 413089 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.3853. Min Act: -0.0000

Data Index: 1119235 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.2331. Min Act: -0.0000

Data Index: 547400 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 5.4102. Min Range: -5.4102

Max Act: 3.5256. Min Act: 0.0001

Data Index: 1622234 (Python Code)

Max Activating Token Index: 198