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

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

Neuron 2944 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3168. Min Range: -4.3168

Max Act: 4.3168. Min Act: -0.0000

Data Index: 1373095 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 4.3168. Min Range: -4.3168

Max Act: 4.1472. Min Act: -0.0000

Data Index: 1504078 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 4.3168. Min Range: -4.3168

Max Act: 4.1051. Min Act: -0.0000

Data Index: 1631482 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.8264. Min Act: -0.0000

Data Index: 1443339 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.7813. Min Act: -0.0000

Data Index: 1499679 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.4843. Min Act: -0.0000

Data Index: 1530077 (Python Code)

Max Activating Token Index: 323

Text #6

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.5800. Min Act: -0.0000

Data Index: 1509377 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.3036. Min Act: -0.0000

Data Index: 1540493 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.7519. Min Act: -0.0000

Data Index: 1374491 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.2467. Min Act: -0.0000

Data Index: 1438433 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.2241. Min Act: -0.0000

Data Index: 1379567 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.1505. Min Act: -0.0000

Data Index: 1645729 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.1165. Min Act: -0.0000

Data Index: 1377680 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.0981. Min Act: -0.0000

Data Index: 1563111 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.0764. Min Act: -0.0000

Data Index: 1397004 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.0703. Min Act: -0.0000

Data Index: 1464330 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.0590. Min Act: -0.0000

Data Index: 1556740 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.1892. Min Act: -0.0000

Data Index: 1483794 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.0351. Min Act: -0.0000

Data Index: 1428415 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 4.3168. Min Range: -4.3168

Max Act: 3.1783. Min Act: -0.0000

Data Index: 1461548 (Python Code)

Max Activating Token Index: 668