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

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

Neuron 3843 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1217854 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8026. Min Act: -0.0000

Data Index: 350635 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8044. Min Act: -0.0000

Data Index: 608101 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7662. Min Act: 0.0000

Data Index: 675214 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7429. Min Act: -0.0000

Data Index: 503238 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7682. Min Act: -0.0000

Data Index: 899261 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7091. Min Act: -0.0000

Data Index: 288694 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7296. Min Act: -0.0000

Data Index: 450521 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6880. Min Act: -0.0000

Data Index: 324580 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6902. Min Act: -0.0000

Data Index: 686662 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1096643 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6452. Min Act: -0.0000

Data Index: 868522 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1203126 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1149631 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6259. Min Act: -0.0000

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1355685 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6487. Min Act: -0.0000

Data Index: 854569 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6025. Min Act: -0.0000

Data Index: 336285 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6154. Min Act: -0.0000

Data Index: 834733 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6089. Min Act: -0.0000

Data Index: 22627 (C4 (Web Text))

Max Activating Token Index: 864