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

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

Neuron 4679 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.9489. Min Act: -0.0000

Data Index: 1104482 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.4502. Min Act: -0.0000

Data Index: 105964 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.1950. Min Act: -0.0000

Data Index: 522923 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.4925. Min Act: -0.0000

Data Index: 193654 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.1892. Min Act: -0.0000

Data Index: 1070606 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.2154. Min Act: -0.0000

Data Index: 366281 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.0096. Min Act: -0.0000

Data Index: 1330249 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7519. Min Act: -0.0000

Data Index: 1050531 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5975. Min Act: -0.0000

Data Index: 712156 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7373. Min Act: -0.0000

Data Index: 335821 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5024. Min Act: -0.0000

Data Index: 850195 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1009205 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.6210. Min Act: -0.0000

Data Index: 195027 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7184. Min Act: -0.0000

Data Index: 1324200 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5801. Min Act: -0.0000

Data Index: 688988 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.6934. Min Act: -0.0000

Data Index: 172730 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5567. Min Act: -0.0000

Data Index: 907625 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5675. Min Act: -0.0000

Data Index: 37151 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.5316. Min Act: -0.0000

Data Index: 289251 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.3942. Min Act: -0.0000

Data Index: 1186929 (C4 (Web Text))

Max Activating Token Index: 845