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

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

Neuron 2107 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.4227. Min Act: 0.0001

Data Index: 1371259 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1498063 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3938. Min Act: 0.0000

Data Index: 1421706 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3631. Min Act: 0.0001

Data Index: 1505143 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1387067 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3499. Min Act: 0.0001

Data Index: 1484320 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3369. Min Act: -0.0000

Data Index: 164380 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3349. Min Act: 0.0001

Data Index: 1626466 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1411102 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3362. Min Act: 0.0001

Data Index: 1422811 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1514074 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3355. Min Act: 0.0001

Data Index: 1599824 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3285. Min Act: 0.0000

Data Index: 1379713 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3142. Min Act: 0.0000

Data Index: 1623320 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3388. Min Act: -0.0000

Data Index: 984837 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1528504 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3487. Min Act: 0.0001

Data Index: 1602583 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3225. Min Act: 0.0001

Data Index: 954297 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3158. Min Act: 0.0001

Data Index: 1426482 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 0.4227. Min Range: -0.4227

Max Act: 0.3007. Min Act: 0.0001

Data Index: 1506702 (Python Code)

Max Activating Token Index: 856