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

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

Neuron 1030 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.9133. Min Act: -0.0000

Data Index: 1467886 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.8354. Min Act: -0.0000

Data Index: 1595622 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.6231. Min Act: -0.0000

Data Index: 1489901 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.1701. Min Act: -0.0000

Data Index: 1369414 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.4009. Min Act: -0.0000

Data Index: 1376403 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.2584. Min Act: -0.0000

Data Index: 1581412 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.0926. Min Act: -0.0000

Data Index: 1390630 (Python Code)

Max Activating Token Index: 491

Text #7

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.9793. Min Act: -0.0000

Data Index: 1448366 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.0676. Min Act: -0.0000

Data Index: 1365382 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 3.9133. Min Range: -3.9133

Max Act: 3.0699. Min Act: -0.0000

Data Index: 1628743 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.9816. Min Act: -0.0000

Data Index: 1627504 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.9382. Min Act: -0.0000

Data Index: 1454493 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.9140. Min Act: -0.0000

Data Index: 1588451 (Python Code)

Max Activating Token Index: 949

Text #13

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.9438. Min Act: -0.0000

Data Index: 1534517 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.6254. Min Act: -0.0000

Data Index: 1423015 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.7331. Min Act: -0.0000

Data Index: 1396878 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.6134. Min Act: -0.0000

Data Index: 1464747 (Python Code)

Max Activating Token Index: 156

Text #17

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.7342. Min Act: -0.0000

Data Index: 1611991 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.7104. Min Act: -0.0000

Data Index: 1526153 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 3.9133. Min Range: -3.9133

Max Act: 2.5875. Min Act: -0.0000

Data Index: 1481350 (Python Code)

Max Activating Token Index: 111