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

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

Neuron 2213 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1095203 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1160580 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9775. Min Act: -0.0000

Data Index: 718697 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9721. Min Act: -0.0000

Data Index: 586712 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0137. Min Act: -0.0000

Data Index: 628492 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1237719 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9277. Min Act: -0.0000

Data Index: 621394 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1326088 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9173. Min Act: -0.0000

Data Index: 321291 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9301. Min Act: -0.0000

Data Index: 165698 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1215989 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.6144. Min Act: -0.0000

Data Index: 22584 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5574. Min Act: -0.0000

Data Index: 416212 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5875. Min Act: -0.0000

Data Index: 787584 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5463. Min Act: -0.0000

Data Index: 466582 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1115255 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5385. Min Act: -0.0000

Data Index: 100483 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5183. Min Act: -0.0000

Data Index: 57817 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5291. Min Act: -0.0000

Data Index: 692419 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.5259. Min Act: -0.0000

Data Index: 900113 (C4 (Web Text))

Max Activating Token Index: 732