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

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

Neuron 3985 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5962. Min Range: -5.5962

Max Act: 5.5962. Min Act: -0.0001

Data Index: 589249 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 5.5962. Min Range: -5.5962

Max Act: 5.0367. Min Act: -0.0001

Data Index: 149441 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 5.5962. Min Range: -5.5962

Max Act: 5.2997. Min Act: -0.0001

Data Index: 437750 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.7901. Min Act: -0.0001

Data Index: 652667 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.4569. Min Act: -0.0001

Data Index: 1074566 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.5285. Min Act: -0.0001

Data Index: 1306498 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.4969. Min Act: -0.0001

Data Index: 786438 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.3695. Min Act: -0.0001

Data Index: 184324 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.3366. Min Act: -0.0001

Data Index: 1247689 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.4406. Min Act: -0.0001

Data Index: 1202441 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.1424. Min Act: -0.0001

Data Index: 1077569 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.5764. Min Act: -0.0001

Data Index: 1343155 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.2539. Min Act: -0.0001

Data Index: 1295532 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.5370. Min Act: -0.0001

Data Index: 836639 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.0630. Min Act: -0.0001

Data Index: 386828 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 5.5962. Min Range: -5.5962

Max Act: 3.8146. Min Act: -0.0001

Data Index: 989826 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.2700. Min Act: -0.0001

Data Index: 1028195 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 5.5962. Min Range: -5.5962

Max Act: 4.1160. Min Act: -0.0001

Data Index: 723663 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 5.5962. Min Range: -5.5962

Max Act: 3.6212. Min Act: -0.0001

Data Index: 664283 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 5.5962. Min Range: -5.5962

Max Act: 3.6394. Min Act: -0.0001

Data Index: 1022638 (C4 (Web Text))

Max Activating Token Index: 679