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

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

Neuron 65 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.9748. Min Act: -0.0001

Data Index: 47588 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.8247. Min Act: -0.0001

Data Index: 604513 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.8703. Min Act: -0.0001

Data Index: 1327092 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.8187. Min Act: -0.0001

Data Index: 1185352 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.6187. Min Act: -0.0001

Data Index: 400061 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 4.0936. Min Range: -4.0936

Max Act: 4.0936. Min Act: -0.0002

Data Index: 967261 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.5329. Min Act: -0.0001

Data Index: 1190694 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.6010. Min Act: -0.0001

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.4404. Min Act: -0.0001

Data Index: 166450 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.5335. Min Act: -0.0001

Data Index: 32515 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.5036. Min Act: -0.0001

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.6750. Min Act: -0.0002

Data Index: 269580 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.3028. Min Act: -0.0001

Data Index: 1008438 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.4353. Min Act: -0.0001

Data Index: 739921 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.4298. Min Act: -0.0001

Data Index: 902765 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.5741. Min Act: -0.0002

Data Index: 148324 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.3991. Min Act: -0.0001

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.7096. Min Act: -0.0001

Data Index: 740020 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.5435. Min Act: -0.0001

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 4.0936. Min Range: -4.0936

Max Act: 3.3935. Min Act: -0.0001

Data Index: 884309 (C4 (Web Text))

Max Activating Token Index: 913