Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3445. Min Act: -0.0004

Data Index: 1462546 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3155. Min Act: -0.0004

Data Index: 1395783 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3448. Min Act: -0.0004

Data Index: 1456260 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3008. Min Act: -0.0004

Data Index: 1567324 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2699. Min Act: -0.0004

Data Index: 1421356 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2895. Min Act: -0.0004

Data Index: 1550888 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2998. Min Act: -0.0004

Data Index: 1370969 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2953. Min Act: -0.0004

Data Index: 1450424 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2965. Min Act: -0.0004

Data Index: 1364625 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2953. Min Act: -0.0004

Data Index: 1634851 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3163. Min Act: -0.0004

Data Index: 1411398 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2889. Min Act: -0.0004

Data Index: 1438096 (Python Code)

Max Activating Token Index: 845

Text #12

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3022. Min Act: -0.0004

Data Index: 1485970 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2791. Min Act: -0.0004

Data Index: 1468046 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2979. Min Act: -0.0004

Data Index: 1625432 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2842. Min Act: -0.0004

Data Index: 1635925 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2956. Min Act: -0.0004

Data Index: 1439882 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2857. Min Act: -0.0004

Data Index: 1407734 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3067. Min Act: -0.0004

Data Index: 1454916 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2839. Min Act: -0.0004

Data Index: 1623232 (Python Code)

Max Activating Token Index: 80