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

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

Neuron 3955 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: 1.3033. Min Range: -1.3033

Max Act: 1.3033. Min Act: -0.0001

Data Index: 693120 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1894. Min Act: -0.0001

Data Index: 614570 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2422. Min Act: -0.0001

Data Index: 381729 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2337. Min Act: -0.0001

Data Index: 146335 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2985. Min Act: -0.0001

Data Index: 1248125 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2227. Min Act: -0.0001

Data Index: 819397 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2780. Min Act: -0.0001

Data Index: 131592 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2036. Min Act: -0.0001

Data Index: 565222 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1929. Min Act: -0.0001

Data Index: 559956 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1238. Min Act: -0.0001

Data Index: 379408 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1536. Min Act: -0.0001

Data Index: 82500 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1397. Min Act: -0.0001

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1646. Min Act: -0.0001

Data Index: 900091 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1824. Min Act: -0.0001

Data Index: 680300 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1886. Min Act: -0.0001

Data Index: 1309398 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1769. Min Act: -0.0001

Data Index: 951860 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.2263. Min Act: -0.0001

Data Index: 56208 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1846. Min Act: -0.0001

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1581. Min Act: -0.0001

Data Index: 625993 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 1.3033. Min Range: -1.3033

Max Act: 1.1411. Min Act: -0.0001

Data Index: 568552 (C4 (Web Text))

Max Activating Token Index: 779