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

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

Neuron 940 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1457541 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1367601 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1415929 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1483087 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1413322 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1378042 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1557738 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1536057 (Python Code)

Max Activating Token Index: 897

Text #8

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9769. Min Act: -0.0000

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1490143 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1458634 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1538360 (Python Code)

Max Activating Token Index: 293

Text #12

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1206528 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8488. Min Act: -0.0000

Data Index: 296263 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9179. Min Act: -0.0000

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1644025 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1451118 (Python Code)

Max Activating Token Index: 455

Text #17

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1601419 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1474182 (Python Code)

Max Activating Token Index: 316

Text #19

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8646. Min Act: -0.0000

Data Index: 133253 (C4 (Web Text))

Max Activating Token Index: 676