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

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

Neuron 3063 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.3576. Min Act: -0.0000

Data Index: 498695 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.2788. Min Act: -0.0000

Data Index: 466301 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1085971 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.0015. Min Act: -0.0000

Data Index: 208962 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.9725. Min Act: -0.0000

Data Index: 670103 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1327991 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.9630. Min Act: -0.0000

Data Index: 151813 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1264544 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.9524. Min Act: -0.0000

Data Index: 577436 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.0067. Min Act: -0.0000

Data Index: 428528 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.9460. Min Act: -0.0000

Data Index: 120634 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.3576. Min Range: -1.3576

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1086964 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1268227 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1170796 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1359052 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.8422. Min Act: -0.0000

Data Index: 453025 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.8946. Min Act: -0.0000

Data Index: 385148 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.8740. Min Act: -0.0000

Data Index: 60706 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.8553. Min Act: -0.0000

Data Index: 745781 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.3576. Min Range: -1.3576

Max Act: 0.8483. Min Act: -0.0000

Data Index: 188774 (C4 (Web Text))

Max Activating Token Index: 90