Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1259 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.6053. Min Act: -0.0000

Data Index: 1576231 (Python Code)

Max Activating Token Index: 247

Text #1

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3997. Min Act: -0.0000

Data Index: 1362823 (Python Code)

Max Activating Token Index: 229

Text #2

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1473084 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1373186 (Python Code)

Max Activating Token Index: 135

Text #4

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1413268 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1531073 (Python Code)

Max Activating Token Index: 424

Text #6

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4196. Min Act: -0.0000

Data Index: 284314 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1413945 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1578978 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1473782 (Python Code)

Max Activating Token Index: 637

Text #10

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3908. Min Act: -0.0000

Data Index: 507041 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3144. Min Act: -0.0000

Data Index: 1625119 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1638481 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3371. Min Act: -0.0000

Data Index: 177297 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2989. Min Act: -0.0000

Data Index: 1062523 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3639. Min Act: -0.0000

Data Index: 169974 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2719. Min Act: -0.0000

Data Index: 579283 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1652887 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1537187 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 1.6053. Min Range: -1.6053

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1402519 (Python Code)

Max Activating Token Index: 121