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

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

Neuron 3118 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: 0.1289. Min Range: -0.1289

Max Act: 0.1262. Min Act: -0.0002

Data Index: 545060 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1289. Min Act: -0.0002

Data Index: 689706 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1171658 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1091. Min Act: -0.0001

Data Index: 173059 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1152291 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1020. Min Act: -0.0002

Data Index: 720732 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1222000 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1028. Min Act: -0.0002

Data Index: 902935 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1209403 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0808. Min Act: -0.0002

Data Index: 467407 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0876. Min Act: -0.0002

Data Index: 44054 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0865. Min Act: -0.0001

Data Index: 104433 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1308373 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0924. Min Act: -0.0001

Data Index: 215345 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0887. Min Act: -0.0002

Data Index: 812844 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0858. Min Act: -0.0002

Data Index: 75433 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0851. Min Act: -0.0002

Data Index: 36128 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0817. Min Act: -0.0001

Data Index: 388117 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1254405 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0871. Min Act: -0.0002

Data Index: 414295 (C4 (Web Text))

Max Activating Token Index: 419