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

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

Neuron 1302 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: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 948 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3089. Min Act: -0.0000

Data Index: 453332 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1138939 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2993. Min Act: -0.0000

Data Index: 606957 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2924. Min Act: -0.0000

Data Index: 717339 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1489995 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2946. Min Act: -0.0001

Data Index: 278560 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2723. Min Act: -0.0000

Data Index: 464223 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2657. Min Act: -0.0001

Data Index: 554984 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2520. Min Act: -0.0000

Data Index: 366902 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2542. Min Act: -0.0000

Data Index: 559359 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2511. Min Act: -0.0000

Data Index: 558868 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2657. Min Act: -0.0001

Data Index: 869903 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2554. Min Act: 0.0000

Data Index: 226751 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2458. Min Act: -0.0000

Data Index: 194479 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2543. Min Act: -0.0000

Data Index: 724777 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2543. Min Act: -0.0000

Data Index: 631782 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1270694 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2429. Min Act: -0.0000

Data Index: 381744 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2514. Min Act: -0.0000

Data Index: 860579 (C4 (Web Text))

Max Activating Token Index: 785