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

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

Neuron 769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3106. Min Range: -6.3106

Max Act: 6.1684. Min Act: -0.0000

Data Index: 1380259 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 6.3106. Min Range: -6.3106

Max Act: 6.0337. Min Act: -0.0000

Data Index: 1531630 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 6.3106. Min Range: -6.3106

Max Act: 6.1704. Min Act: -0.0000

Data Index: 1587761 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 6.3106. Min Range: -6.3106

Max Act: 6.3106. Min Act: -0.0000

Data Index: 1458855 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.8174. Min Act: -0.0000

Data Index: 1388600 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.7118. Min Act: -0.0000

Data Index: 1611371 (Python Code)

Max Activating Token Index: 599

Text #6

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.6472. Min Act: -0.0000

Data Index: 1582238 (Python Code)

Max Activating Token Index: 935

Text #7

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.7872. Min Act: -0.0000

Data Index: 1420092 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.4593. Min Act: -0.0000

Data Index: 1410719 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.4166. Min Act: -0.0000

Data Index: 1551549 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.2050. Min Act: -0.0000

Data Index: 1400969 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.3739. Min Act: -0.0000

Data Index: 1522273 (Python Code)

Max Activating Token Index: 1015

Text #12

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.3487. Min Act: -0.0000

Data Index: 1570958 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.5232. Min Act: -0.0000

Data Index: 1518782 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.3239. Min Act: -0.0000

Data Index: 1454105 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.3137. Min Act: -0.0000

Data Index: 1551761 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.2860. Min Act: -0.0000

Data Index: 1540348 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.2547. Min Act: -0.0000

Data Index: 1405022 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.4517. Min Act: -0.0000

Data Index: 1401181 (Python Code)

Max Activating Token Index: 517

Text #19

Max Range: 6.3106. Min Range: -6.3106

Max Act: 5.2345. Min Act: -0.0000

Data Index: 1605738 (Python Code)

Max Activating Token Index: 453