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

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

Neuron 5109 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.8089. Min Act: -0.0001

Data Index: 1645156 (Python Code)

Max Activating Token Index: 66

Text #1

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.7552. Min Act: -0.0001

Data Index: 1489579 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.7475. Min Act: -0.0001

Data Index: 1652390 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.7390. Min Act: -0.0001

Data Index: 1605939 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6802. Min Act: -0.0001

Data Index: 1608631 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6666. Min Act: -0.0001

Data Index: 1462030 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6555. Min Act: -0.0001

Data Index: 1557819 (Python Code)

Max Activating Token Index: 348

Text #7

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6961. Min Act: -0.0001

Data Index: 1623974 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6689. Min Act: -0.0001

Data Index: 1567781 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6425. Min Act: -0.0001

Data Index: 1427038 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6135. Min Act: -0.0001

Data Index: 1468989 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6113. Min Act: -0.0001

Data Index: 1613181 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6071. Min Act: -0.0001

Data Index: 1461584 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6090. Min Act: -0.0001

Data Index: 1562494 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6149. Min Act: -0.0001

Data Index: 1508680 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.5957. Min Act: -0.0001

Data Index: 1405674 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.5976. Min Act: -0.0001

Data Index: 1440205 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.5701. Min Act: -0.0001

Data Index: 1534039 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.6060. Min Act: -0.0001

Data Index: 1526067 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 1.8089. Min Range: -1.8089

Max Act: 1.5747. Min Act: -0.0001

Data Index: 1383383 (Python Code)

Max Activating Token Index: 28