Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.7907. Min Act: -0.0000

Data Index: 438368 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 4.0864. Min Range: -4.0864

Max Act: 4.0864. Min Act: -0.0000

Data Index: 1123738 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.4735. Min Act: -0.0000

Data Index: 529840 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.7826. Min Act: -0.0000

Data Index: 71159 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.4342. Min Act: -0.0000

Data Index: 885115 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.3902. Min Act: -0.0000

Data Index: 375402 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.4028. Min Act: -0.0000

Data Index: 341442 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.1958. Min Act: -0.0000

Data Index: 1145127 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2094. Min Act: -0.0000

Data Index: 139004 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.1683. Min Act: -0.0000

Data Index: 949518 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.3020. Min Act: -0.0000

Data Index: 927200 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.1556. Min Act: -0.0000

Data Index: 815569 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2990. Min Act: -0.0000

Data Index: 629519 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2565. Min Act: -0.0000

Data Index: 501416 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2561. Min Act: -0.0000

Data Index: 178084 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2192. Min Act: -0.0000

Data Index: 1248786 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2209. Min Act: -0.0000

Data Index: 620070 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.2079. Min Act: -0.0000

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.1983. Min Act: -0.0000

Data Index: 752105 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 4.0864. Min Range: -4.0864

Max Act: 3.1818. Min Act: -0.0000

Data Index: 805544 (C4 (Web Text))

Max Activating Token Index: 824