Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2083 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3780. Min Range: -6.3780

Max Act: 6.3780. Min Act: -0.0000

Data Index: 853259 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.8554. Min Act: -0.0000

Data Index: 1286720 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.7398. Min Act: -0.0000

Data Index: 1019398 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.6483. Min Act: -0.0000

Data Index: 1211914 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.2658. Min Act: -0.0000

Data Index: 149660 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.2413. Min Act: -0.0000

Data Index: 279210 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.3916. Min Act: -0.0000

Data Index: 855366 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 6.3780. Min Range: -6.3780

Max Act: 5.0354. Min Act: -0.0000

Data Index: 1211967 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.9289. Min Act: -0.0000

Data Index: 137950 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.8857. Min Act: -0.0000

Data Index: 77327 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.6994. Min Act: -0.0000

Data Index: 732145 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.3614. Min Act: -0.0000

Data Index: 1148045 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.6483. Min Act: -0.0000

Data Index: 431038 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.6474. Min Act: -0.0000

Data Index: 624224 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.7400. Min Act: -0.0000

Data Index: 741784 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.7594. Min Act: -0.0000

Data Index: 884261 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.7173. Min Act: -0.0000

Data Index: 476160 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.4822. Min Act: -0.0000

Data Index: 859193 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.2681. Min Act: -0.0000

Data Index: 459006 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 6.3780. Min Range: -6.3780

Max Act: 4.0312. Min Act: -0.0000

Data Index: 528579 (C4 (Web Text))

Max Activating Token Index: 370