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

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

Neuron 2135 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.6764. Min Act: -0.0000

Data Index: 759089 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.8155. Min Act: -0.0000

Data Index: 413376 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 2.8155. Min Range: -2.8155

Max Act: 2.4561. Min Act: -0.0000

Data Index: 711392 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.7299. Min Act: -0.0000

Data Index: 1172372 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.7262. Min Act: -0.0000

Data Index: 358186 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.9154. Min Act: -0.0000

Data Index: 544824 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.8666. Min Act: -0.0000

Data Index: 209701 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.3828. Min Act: -0.0001

Data Index: 344061 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.7133. Min Act: -0.0000

Data Index: 271670 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1336598 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.4331. Min Act: -0.0000

Data Index: 194898 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.5058. Min Act: -0.0000

Data Index: 848577 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.4835. Min Act: -0.0000

Data Index: 733619 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1028055 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.3942. Min Act: -0.0000

Data Index: 216810 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.4397. Min Act: -0.0000

Data Index: 624086 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.5450. Min Act: -0.0000

Data Index: 849119 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.3464. Min Act: -0.0000

Data Index: 848150 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.3791. Min Act: -0.0000

Data Index: 681396 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 2.8155. Min Range: -2.8155

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1282930 (C4 (Web Text))

Max Activating Token Index: 289