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

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

Neuron 2663 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1188390 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0140. Min Act: -0.0001

Data Index: 920529 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0486. Min Act: -0.0001

Data Index: 674172 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0169. Min Act: -0.0001

Data Index: 132491 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9439. Min Act: -0.0001

Data Index: 760658 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1315733 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9590. Min Act: -0.0001

Data Index: 919725 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8990. Min Act: -0.0001

Data Index: 827753 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9104. Min Act: -0.0001

Data Index: 1047396 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9127. Min Act: -0.0001

Data Index: 880158 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9301. Min Act: -0.0001

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8816. Min Act: -0.0001

Data Index: 514995 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8904. Min Act: -0.0001

Data Index: 645215 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8962. Min Act: -0.0001

Data Index: 1102112 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8992. Min Act: -0.0001

Data Index: 217565 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9168. Min Act: -0.0001

Data Index: 697188 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8523. Min Act: -0.0001

Data Index: 419896 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8425. Min Act: -0.0001

Data Index: 91255 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1291510 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8933. Min Act: -0.0001

Data Index: 541228 (C4 (Web Text))

Max Activating Token Index: 850