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

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

Neuron 6095 in Layer 1

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: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0002

Data Index: 1646359 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4541. Min Act: -0.0002

Data Index: 1593517 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4552. Min Act: -0.0002

Data Index: 1657019 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4409. Min Act: -0.0002

Data Index: 1567766 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4389. Min Act: -0.0002

Data Index: 1377310 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4159. Min Act: -0.0002

Data Index: 1391172 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4148. Min Act: -0.0002

Data Index: 1624627 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4121. Min Act: -0.0002

Data Index: 1371486 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4128. Min Act: -0.0002

Data Index: 1413686 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3932. Min Act: -0.0002

Data Index: 1431890 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3904. Min Act: -0.0002

Data Index: 1631105 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3944. Min Act: -0.0002

Data Index: 1600885 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3945. Min Act: -0.0002

Data Index: 1589823 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3891. Min Act: -0.0002

Data Index: 1412104 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3925. Min Act: -0.0002

Data Index: 1470295 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3941. Min Act: -0.0002

Data Index: 1514023 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3915. Min Act: -0.0002

Data Index: 1586370 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3963. Min Act: -0.0002

Data Index: 1645291 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3921. Min Act: -0.0002

Data Index: 1568808 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3819. Min Act: -0.0002

Data Index: 1418674 (Python Code)

Max Activating Token Index: 86