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

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

Neuron 2134 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: 4.2461. Min Range: -4.2461

Max Act: 4.1844. Min Act: -0.0000

Data Index: 240309 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1526. Min Act: -0.0000

Data Index: 1160338 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.2461. Min Act: -0.0000

Data Index: 521778 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.2404. Min Act: -0.0000

Data Index: 1079117 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1738. Min Act: -0.0000

Data Index: 797047 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1565. Min Act: -0.0000

Data Index: 598180 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1489. Min Act: -0.0000

Data Index: 1073994 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1512. Min Act: -0.0000

Data Index: 535657 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 4.2461. Min Range: -4.2461

Max Act: 3.9449. Min Act: -0.0000

Data Index: 176986 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.2447. Min Act: -0.0000

Data Index: 474398 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0522. Min Act: -0.0000

Data Index: 996310 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1547. Min Act: -0.0000

Data Index: 903446 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 4.2461. Min Range: -4.2461

Max Act: 2.9657. Min Act: -0.0000

Data Index: 1152303 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 4.2461. Min Range: -4.2461

Max Act: 2.9119. Min Act: -0.0000

Data Index: 535381 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 4.2461. Min Range: -4.2461

Max Act: 1.6505. Min Act: -0.0000

Data Index: 1386512 (Python Code)

Max Activating Token Index: 775

Text #15

Max Range: 4.2461. Min Range: -4.2461

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1365691 (Python Code)

Max Activating Token Index: 672

Text #16

Max Range: 4.2461. Min Range: -4.2461

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1614240 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 4.2461. Min Range: -4.2461

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1483150 (Python Code)

Max Activating Token Index: 520

Text #18

Max Range: 4.2461. Min Range: -4.2461

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1606902 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 4.2461. Min Range: -4.2461

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1536987 (Python Code)

Max Activating Token Index: 988