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

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

Neuron 3632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1070821 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1150371 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5038. Min Act: -0.0000

Data Index: 989940 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4819. Min Act: -0.0000

Data Index: 145858 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4771. Min Act: -0.0000

Data Index: 713925 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4564. Min Act: -0.0000

Data Index: 267501 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4522. Min Act: -0.0000

Data Index: 646942 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1057798 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4518. Min Act: -0.0000

Data Index: 285708 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4572. Min Act: -0.0000

Data Index: 63639 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.3973. Min Act: -0.0000

Data Index: 288169 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4397. Min Act: -0.0000

Data Index: 851463 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1089771 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4220. Min Act: -0.0000

Data Index: 611938 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4475. Min Act: -0.0000

Data Index: 669590 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4110. Min Act: -0.0000

Data Index: 844668 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4056. Min Act: -0.0000

Data Index: 781456 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1350090 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4319. Min Act: -0.0000

Data Index: 48354 (C4 (Web Text))

Max Activating Token Index: 497