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

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

Neuron 3123 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: 0.4825. Min Range: -0.4825

Max Act: 0.4472. Min Act: -0.0002

Data Index: 1160703 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.4825. Min Act: -0.0001

Data Index: 321150 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3186. Min Act: -0.0002

Data Index: 183062 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3082. Min Act: -0.0002

Data Index: 497042 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1093548 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3132. Min Act: -0.0002

Data Index: 824703 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3135. Min Act: -0.0002

Data Index: 1339474 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3020. Min Act: -0.0001

Data Index: 320424 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1075972 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3001. Min Act: -0.0002

Data Index: 179623 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3013. Min Act: -0.0002

Data Index: 690370 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2969. Min Act: -0.0001

Data Index: 874296 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3075. Min Act: -0.0002

Data Index: 447091 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3217. Min Act: -0.0001

Data Index: 165781 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2876. Min Act: -0.0001

Data Index: 539086 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2970. Min Act: -0.0001

Data Index: 892287 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2961. Min Act: -0.0002

Data Index: 434820 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2945. Min Act: -0.0002

Data Index: 1108052 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2904. Min Act: -0.0002

Data Index: 948909 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2816. Min Act: -0.0002

Data Index: 625946 (C4 (Web Text))

Max Activating Token Index: 995