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

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

Neuron 2903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4612. Min Act: -0.0000

Data Index: 446301 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1321051 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3817. Min Act: -0.0000

Data Index: 684448 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3565. Min Act: -0.0001

Data Index: 525962 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1131561 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3573. Min Act: -0.0000

Data Index: 82514 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3546. Min Act: -0.0000

Data Index: 292543 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3555. Min Act: -0.0000

Data Index: 353088 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3373. Min Act: -0.0001

Data Index: 637151 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3464. Min Act: -0.0000

Data Index: 17307 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3203. Min Act: -0.0000

Data Index: 310266 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3122. Min Act: -0.0001

Data Index: 521359 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3046. Min Act: -0.0000

Data Index: 43503 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3151. Min Act: -0.0000

Data Index: 717906 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3025. Min Act: -0.0000

Data Index: 164006 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3227. Min Act: -0.0000

Data Index: 754852 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1323309 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3091. Min Act: -0.0000

Data Index: 916908 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1209894 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3118. Min Act: -0.0001

Data Index: 1257614 (C4 (Web Text))

Max Activating Token Index: 196