Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 900 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1489. Min Act: -0.0001

Data Index: 529494 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1224. Min Act: -0.0001

Data Index: 481940 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1452. Min Act: -0.0001

Data Index: 1182220 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0284. Min Act: -0.0001

Data Index: 729954 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1074579 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8833. Min Act: -0.0001

Data Index: 1216068 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8314. Min Act: -0.0001

Data Index: 996009 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.9059. Min Act: -0.0001

Data Index: 128802 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.9076. Min Act: -0.0001

Data Index: 1270192 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8806. Min Act: -0.0001

Data Index: 588004 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8875. Min Act: -0.0001

Data Index: 878379 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.9035. Min Act: -0.0001

Data Index: 111763 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.9596. Min Act: -0.0001

Data Index: 839415 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8993. Min Act: -0.0001

Data Index: 1341221 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8925. Min Act: -0.0001

Data Index: 450190 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8890. Min Act: -0.0001

Data Index: 56166 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8943. Min Act: -0.0001

Data Index: 134149 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.9445. Min Act: -0.0001

Data Index: 772833 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8581. Min Act: -0.0001

Data Index: 610503 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1196682 (C4 (Web Text))

Max Activating Token Index: 169