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

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

Neuron 1646 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3587. Min Act: -0.0001

Data Index: 653250 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3423. Min Act: -0.0001

Data Index: 732147 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3310. Min Act: -0.0002

Data Index: 1313931 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3423. Min Act: -0.0001

Data Index: 80274 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3513. Min Act: -0.0002

Data Index: 976520 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3347. Min Act: -0.0002

Data Index: 751524 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3183. Min Act: -0.0002

Data Index: 839109 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3292. Min Act: -0.0002

Data Index: 1317399 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3296. Min Act: -0.0002

Data Index: 752826 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3174. Min Act: -0.0002

Data Index: 1117731 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3485. Min Act: -0.0001

Data Index: 1002960 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1245983 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3459. Min Act: -0.0001

Data Index: 116886 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3291. Min Act: -0.0002

Data Index: 841800 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2977. Min Act: -0.0001

Data Index: 807371 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3244. Min Act: -0.0002

Data Index: 1040622 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3179. Min Act: -0.0001

Data Index: 894543 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3232. Min Act: -0.0002

Data Index: 1011817 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3023. Min Act: -0.0002

Data Index: 341515 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3135. Min Act: -0.0002

Data Index: 672508 (C4 (Web Text))

Max Activating Token Index: 826