Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2054 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3739. Min Act: -0.0001

Data Index: 1431948 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3540. Min Act: -0.0001

Data Index: 1495954 (Python Code)

Max Activating Token Index: 897

Text #2

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3568. Min Act: -0.0001

Data Index: 1382095 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3568. Min Act: -0.0001

Data Index: 1536294 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3242. Min Act: -0.0001

Data Index: 1577577 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1590827 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1385946 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3442. Min Act: -0.0001

Data Index: 1502291 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3441. Min Act: -0.0001

Data Index: 1578217 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1604355 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1599161 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3174. Min Act: -0.0001

Data Index: 1576109 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1541413 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1457220 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1569116 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3162. Min Act: -0.0001

Data Index: 1605374 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1602568 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3129. Min Act: -0.0001

Data Index: 1498692 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1510389 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2998. Min Act: -0.0001

Data Index: 1457534 (Python Code)

Max Activating Token Index: 170