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

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

Neuron 3979 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6970. Min Act: -0.0001

Data Index: 1496742 (Python Code)

Max Activating Token Index: 555

Text #1

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.9045. Min Act: -0.0001

Data Index: 1403441 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.8930. Min Act: -0.0001

Data Index: 1532072 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.9428. Min Act: -0.0001

Data Index: 1407837 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.8164. Min Act: -0.0001

Data Index: 1435562 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.8074. Min Act: -0.0001

Data Index: 1638301 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.7730. Min Act: -0.0001

Data Index: 1526448 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.8897. Min Act: -0.0001

Data Index: 1411362 (Python Code)

Max Activating Token Index: 861

Text #8

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6567. Min Act: -0.0001

Data Index: 821706 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.7489. Min Act: -0.0001

Data Index: 1590790 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.4364. Min Act: -0.0001

Data Index: 1511700 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.5529. Min Act: -0.0001

Data Index: 1544918 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6339. Min Act: -0.0001

Data Index: 1632957 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.7199. Min Act: -0.0001

Data Index: 1606284 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.7371. Min Act: -0.0001

Data Index: 1553561 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.5997. Min Act: -0.0001

Data Index: 1380615 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6822. Min Act: -0.0001

Data Index: 1538870 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.9803. Min Act: -0.0001

Data Index: 1655740 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.6417. Min Act: -0.0001

Data Index: 1652075 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 1.9803. Min Range: -1.9803

Max Act: 1.3857. Min Act: -0.0001

Data Index: 1371628 (Python Code)

Max Activating Token Index: 894