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

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

Neuron 1141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1203968 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2182. Min Act: -0.0000

Data Index: 381618 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2051. Min Act: -0.0001

Data Index: 1143200 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1071574 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2084. Min Act: -0.0001

Data Index: 247594 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2091. Min Act: -0.0000

Data Index: 502703 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1218955 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1972. Min Act: -0.0001

Data Index: 427763 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2040. Min Act: -0.0001

Data Index: 782788 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1352464 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1891. Min Act: -0.0001

Data Index: 414652 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1898. Min Act: -0.0001

Data Index: 779633 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1815. Min Act: -0.0001

Data Index: 591990 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1823. Min Act: -0.0001

Data Index: 595801 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1259664 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1992. Min Act: -0.0000

Data Index: 997783 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1861. Min Act: -0.0000

Data Index: 90000 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1861. Min Act: -0.0001

Data Index: 423308 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1343064 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.2198. Min Range: -0.2198

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1262645 (C4 (Web Text))

Max Activating Token Index: 781