Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8996. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8078. Min Act: -0.0000

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7555. Min Act: -0.0000

Data Index: 526248 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7653. Min Act: -0.0000

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1589578 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1638787 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1421740 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6540. Min Act: -0.0000

Data Index: 659397 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1299928 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1298230 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1095563 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5547. Min Act: -0.0000

Data Index: 207489 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1273539 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1319662 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5057. Min Act: -0.0000

Data Index: 588129 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1110146 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1107035 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5119. Min Act: -0.0000

Data Index: 468613 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1201182 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.5208. Min Act: -0.0000

Data Index: 350959 (C4 (Web Text))

Max Activating Token Index: 85