Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4713 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3258. Min Act: -0.0000

Data Index: 933747 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3120. Min Act: -0.0000

Data Index: 678949 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2956. Min Act: -0.0000

Data Index: 350022 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1226962 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2881. Min Act: -0.0000

Data Index: 85984 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1257926 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3112. Min Act: -0.0000

Data Index: 406987 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3056. Min Act: -0.0000

Data Index: 735016 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2914. Min Act: -0.0000

Data Index: 425749 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2760. Min Act: -0.0000

Data Index: 464546 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2862. Min Act: -0.0000

Data Index: 388950 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2687. Min Act: -0.0000

Data Index: 85049 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2886. Min Act: -0.0000

Data Index: 666363 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2803. Min Act: -0.0000

Data Index: 711987 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2660. Min Act: -0.0000

Data Index: 921538 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2657. Min Act: -0.0000

Data Index: 589052 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2713. Min Act: -0.0000

Data Index: 815912 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1312500 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2479. Min Act: -0.0000

Data Index: 165021 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1327294 (C4 (Web Text))

Max Activating Token Index: 173