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

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

Neuron 2014 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: 1.6645. Min Range: -1.6645

Max Act: 1.6645. Min Act: -0.0001

Data Index: 378371 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.6280. Min Act: -0.0001

Data Index: 298376 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5761. Min Act: -0.0001

Data Index: 383287 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1143313 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4725. Min Act: -0.0001

Data Index: 1198352 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3250. Min Act: -0.0000

Data Index: 809945 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3787. Min Act: -0.0001

Data Index: 1185270 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4005. Min Act: -0.0001

Data Index: 803802 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3891. Min Act: -0.0000

Data Index: 731604 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.3525. Min Act: -0.0001

Data Index: 587478 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.4490. Min Act: -0.0001

Data Index: 700202 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2330. Min Act: -0.0000

Data Index: 370262 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2094. Min Act: -0.0001

Data Index: 204152 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.1570. Min Act: -0.0000

Data Index: 173808 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2237. Min Act: -0.0001

Data Index: 457286 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2550. Min Act: -0.0001

Data Index: 615793 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.1757. Min Act: -0.0000

Data Index: 630360 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.0965. Min Act: -0.0000

Data Index: 859266 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.2057. Min Act: -0.0001

Data Index: 146800 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.6645. Min Range: -1.6645

Max Act: 1.1107. Min Act: -0.0000

Data Index: 150946 (C4 (Web Text))

Max Activating Token Index: 286