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

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

Neuron 1005 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: 0.3460. Min Range: -0.3460

Max Act: 0.3460. Min Act: -0.0001

Data Index: 531189 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3281. Min Act: -0.0002

Data Index: 717486 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3314. Min Act: -0.0002

Data Index: 1268456 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3182. Min Act: -0.0001

Data Index: 227547 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2982. Min Act: -0.0002

Data Index: 923328 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3056. Min Act: -0.0002

Data Index: 244256 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1128748 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2967. Min Act: -0.0001

Data Index: 877089 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3133. Min Act: -0.0002

Data Index: 727031 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2869. Min Act: -0.0001

Data Index: 58290 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3043. Min Act: -0.0001

Data Index: 487826 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2938. Min Act: -0.0002

Data Index: 918084 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1187954 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3019. Min Act: -0.0002

Data Index: 153253 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2860. Min Act: -0.0002

Data Index: 892303 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2829. Min Act: -0.0002

Data Index: 830563 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2857. Min Act: -0.0001

Data Index: 937394 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3065. Min Act: -0.0002

Data Index: 648810 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2942. Min Act: -0.0001

Data Index: 685018 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2763. Min Act: -0.0002

Data Index: 853109 (C4 (Web Text))

Max Activating Token Index: 359