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

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

Neuron 1195 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: 4.2613. Min Range: -4.2613

Max Act: 4.0690. Min Act: -0.0001

Data Index: 1079088 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 4.2613. Min Range: -4.2613

Max Act: 4.2613. Min Act: -0.0001

Data Index: 1027155 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 4.2613. Min Range: -4.2613

Max Act: 4.0654. Min Act: -0.0001

Data Index: 1010170 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.9037. Min Act: -0.0001

Data Index: 1101350 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.7976. Min Act: -0.0001

Data Index: 768894 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.9171. Min Act: -0.0001

Data Index: 707834 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.4640. Min Act: -0.0001

Data Index: 997282 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.5646. Min Act: -0.0001

Data Index: 360958 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.5072. Min Act: -0.0001

Data Index: 139228 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.4394. Min Act: -0.0001

Data Index: 197582 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.2468. Min Act: -0.0001

Data Index: 534825 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.2816. Min Act: -0.0001

Data Index: 941423 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.1114. Min Act: -0.0001

Data Index: 12477 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.0871. Min Act: -0.0001

Data Index: 780629 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.0211. Min Act: -0.0001

Data Index: 41329 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 4.2613. Min Range: -4.2613

Max Act: 2.9211. Min Act: -0.0001

Data Index: 721069 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 4.2613. Min Range: -4.2613

Max Act: 2.7425. Min Act: -0.0001

Data Index: 948520 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 4.2613. Min Range: -4.2613

Max Act: 3.0279. Min Act: -0.0001

Data Index: 1160299 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 4.2613. Min Range: -4.2613

Max Act: 2.7288. Min Act: -0.0001

Data Index: 1063942 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 4.2613. Min Range: -4.2613

Max Act: 2.9795. Min Act: -0.0001

Data Index: 1267817 (C4 (Web Text))

Max Activating Token Index: 613