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

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

Neuron 1462 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: 0.3835. Min Range: -0.3835

Max Act: 0.3646. Min Act: -0.0001

Data Index: 116569 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3612. Min Act: -0.0001

Data Index: 249916 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3348. Min Act: -0.0001

Data Index: 872508 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3835. Min Act: -0.0001

Data Index: 903030 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3131. Min Act: -0.0001

Data Index: 11500 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3395. Min Act: -0.0001

Data Index: 826313 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2820. Min Act: -0.0001

Data Index: 573201 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3240. Min Act: -0.0001

Data Index: 585720 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1210889 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2991. Min Act: -0.0001

Data Index: 977211 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3023. Min Act: -0.0001

Data Index: 351192 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2297. Min Act: -0.0001

Data Index: 307302 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2763. Min Act: -0.0001

Data Index: 581405 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.3164. Min Act: -0.0001

Data Index: 1191068 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1189611 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2956. Min Act: -0.0001

Data Index: 465633 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2747. Min Act: -0.0001

Data Index: 578979 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.3835. Min Range: -0.3835

Max Act: 0.2751. Min Act: -0.0001

Data Index: 449969 (C4 (Web Text))

Max Activating Token Index: 692