Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2667 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3602. Min Act: -0.0001

Data Index: 1414410 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1437922 (Python Code)

Max Activating Token Index: 234

Text #2

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1445773 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3386. Min Act: -0.0001

Data Index: 1503014 (Python Code)

Max Activating Token Index: 929

Text #4

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3384. Min Act: -0.0001

Data Index: 1370896 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1599708 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1422654 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3322. Min Act: -0.0001

Data Index: 1446735 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1612934 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3317. Min Act: -0.0001

Data Index: 1502247 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1471848 (Python Code)

Max Activating Token Index: 405

Text #11

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1450864 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3299. Min Act: -0.0001

Data Index: 1487050 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3070. Min Act: -0.0001

Data Index: 1380429 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1596360 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2821. Min Act: -0.0001

Data Index: 1551052 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3023. Min Act: -0.0001

Data Index: 1457090 (Python Code)

Max Activating Token Index: 284

Text #17

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1576070 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1427930 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1547998 (Python Code)

Max Activating Token Index: 126