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

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

Neuron 2935 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: 0.8975. Min Range: -0.8975

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1497056 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1634209 (Python Code)

Max Activating Token Index: 740

Text #2

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1376547 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1455376 (Python Code)

Max Activating Token Index: 923

Text #4

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1542669 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8058. Min Act: -0.0000

Data Index: 200864 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1628750 (Python Code)

Max Activating Token Index: 465

Text #7

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1439402 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1472486 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6875. Min Act: -0.0000

Data Index: 733284 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1389761 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7289. Min Act: -0.0000

Data Index: 867394 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1466949 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7588. Min Act: -0.0000

Data Index: 963343 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1641963 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7350. Min Act: -0.0000

Data Index: 375392 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7566. Min Act: -0.0000

Data Index: 138331 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7082. Min Act: -0.0000

Data Index: 644512 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1222337 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.8975. Min Range: -0.8975

Max Act: 0.7343. Min Act: -0.0000

Data Index: 838644 (C4 (Web Text))

Max Activating Token Index: 911