Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1738 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5405. Min Act: -0.0002

Data Index: 1001387 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4449. Min Act: -0.0002

Data Index: 300543 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4259. Min Act: -0.0002

Data Index: 521130 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4661. Min Act: -0.0002

Data Index: 970240 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4202. Min Act: -0.0002

Data Index: 1263094 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4534. Min Act: -0.0002

Data Index: 976945 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4236. Min Act: -0.0002

Data Index: 1060280 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4058. Min Act: -0.0002

Data Index: 125897 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4236. Min Act: -0.0002

Data Index: 1114191 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3688. Min Act: -0.0002

Data Index: 1648581 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4228. Min Act: -0.0002

Data Index: 906968 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3999. Min Act: -0.0002

Data Index: 250294 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3650. Min Act: -0.0002

Data Index: 688330 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4168. Min Act: -0.0002

Data Index: 103601 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3772. Min Act: -0.0002

Data Index: 226689 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3658. Min Act: -0.0002

Data Index: 787105 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3564. Min Act: -0.0002

Data Index: 87698 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4093. Min Act: -0.0002

Data Index: 206906 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3881. Min Act: -0.0002

Data Index: 1124044 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3801. Min Act: -0.0002

Data Index: 629956 (C4 (Web Text))

Max Activating Token Index: 935