Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3177 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.4030. Min Act: -0.0001

Data Index: 1553936 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3681. Min Act: -0.0001

Data Index: 1498652 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1589495 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1384756 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1503939 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1533383 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3367. Min Act: -0.0001

Data Index: 1527901 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3225. Min Act: -0.0001

Data Index: 1537233 (Python Code)

Max Activating Token Index: 59

Text #8

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1610748 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3289. Min Act: -0.0001

Data Index: 1539245 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1533248 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1398974 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3092. Min Act: -0.0001

Data Index: 1482819 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3077. Min Act: -0.0001

Data Index: 1552552 (Python Code)

Max Activating Token Index: 183

Text #14

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1562620 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1607566 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1423070 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1387745 (Python Code)

Max Activating Token Index: 333

Text #18

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2943. Min Act: -0.0001

Data Index: 1650082 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 0.4030. Min Range: -0.4030

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1554442 (Python Code)

Max Activating Token Index: 35