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

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

Neuron 1927 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1036430 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3568. Min Act: 0.0000

Data Index: 762498 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1313407 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.2559. Min Act: -0.0000

Data Index: 33521 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.2107. Min Act: -0.0000

Data Index: 718329 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.2797. Min Act: 0.0000

Data Index: 962911 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1771. Min Act: -0.0000

Data Index: 843403 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1266999 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1398. Min Act: -0.0000

Data Index: 824636 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1309. Min Act: -0.0000

Data Index: 588171 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1136. Min Act: -0.0000

Data Index: 774904 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0728. Min Act: -0.0000

Data Index: 237782 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0743. Min Act: -0.0000

Data Index: 726853 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1185. Min Act: -0.0000

Data Index: 574582 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1153943 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0335. Min Act: -0.0000

Data Index: 867540 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9683. Min Act: -0.0000

Data Index: 590020 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1250041 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0021. Min Act: -0.0000

Data Index: 740439 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9219. Min Act: 0.0000

Data Index: 418935 (C4 (Web Text))

Max Activating Token Index: 741