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

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

Neuron 3746 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1604932 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2165. Min Act: 0.0001

Data Index: 1570074 (Python Code)

Max Activating Token Index: 569

Text #2

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2123. Min Act: 0.0001

Data Index: 1466858 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1530727 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2095. Min Act: 0.0000

Data Index: 1455772 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2104. Min Act: 0.0001

Data Index: 1506972 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1986. Min Act: 0.0001

Data Index: 1648915 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1595091 (Python Code)

Max Activating Token Index: 965

Text #8

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1956. Min Act: 0.0001

Data Index: 1509021 (Python Code)

Max Activating Token Index: 909

Text #9

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1908. Min Act: 0.0001

Data Index: 1513895 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1960. Min Act: 0.0001

Data Index: 1534063 (Python Code)

Max Activating Token Index: 729

Text #11

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1942. Min Act: 0.0001

Data Index: 1611611 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1927. Min Act: 0.0000

Data Index: 1431673 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1932. Min Act: 0.0000

Data Index: 1537736 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1964. Min Act: 0.0001

Data Index: 1640988 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1406044 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1893. Min Act: 0.0000

Data Index: 1517264 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1896. Min Act: 0.0001

Data Index: 1505139 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1890. Min Act: 0.0001

Data Index: 1574998 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1593127 (Python Code)

Max Activating Token Index: 614