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

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

Neuron 264 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: 1.7305. Min Range: -1.7305

Max Act: 1.7305. Min Act: -0.0001

Data Index: 399056 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.4257. Min Act: -0.0001

Data Index: 863901 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.3409. Min Act: -0.0001

Data Index: 879335 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1927. Min Act: -0.0001

Data Index: 545457 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.2633. Min Act: -0.0001

Data Index: 193650 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.3363. Min Act: -0.0001

Data Index: 759765 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1845. Min Act: -0.0001

Data Index: 1071077 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.2482. Min Act: -0.0001

Data Index: 123215 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1481. Min Act: -0.0001

Data Index: 831781 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1547. Min Act: -0.0001

Data Index: 1248360 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.2086. Min Act: -0.0001

Data Index: 1095343 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.2060. Min Act: -0.0001

Data Index: 229924 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1962. Min Act: -0.0001

Data Index: 882389 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1837. Min Act: -0.0001

Data Index: 605513 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1076. Min Act: -0.0001

Data Index: 648146 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.0425. Min Act: -0.0001

Data Index: 717064 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1311. Min Act: -0.0001

Data Index: 909530 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.0938. Min Act: -0.0001

Data Index: 1266888 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.0513. Min Act: -0.0001

Data Index: 1209519 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.7305. Min Range: -1.7305

Max Act: 1.1331. Min Act: -0.0001

Data Index: 701717 (C4 (Web Text))

Max Activating Token Index: 116