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

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

Neuron 1377 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2325. Min Act: -0.0001

Data Index: 632257 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2241. Min Act: -0.0001

Data Index: 636890 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2053. Min Act: -0.0001

Data Index: 922212 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2141. Min Act: -0.0001

Data Index: 280513 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1978. Min Act: -0.0001

Data Index: 868935 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1031327 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2039. Min Act: -0.0001

Data Index: 638813 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1939. Min Act: -0.0001

Data Index: 796636 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1898. Min Act: -0.0001

Data Index: 176370 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1007042 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1816. Min Act: -0.0001

Data Index: 709550 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1233632 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1914. Min Act: -0.0001

Data Index: 821753 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1946. Min Act: -0.0001

Data Index: 984212 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1743. Min Act: -0.0001

Data Index: 462029 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1152811 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1170815 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1709. Min Act: -0.0001

Data Index: 985206 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1006733 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1830. Min Act: -0.0001

Data Index: 454385 (C4 (Web Text))

Max Activating Token Index: 428