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

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

Neuron 3131 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4053. Min Act: -0.0000

Data Index: 989703 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1303216 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1057152 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1185316 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3182. Min Act: -0.0000

Data Index: 689354 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1310317 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3068. Min Act: -0.0000

Data Index: 28154 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2885. Min Act: -0.0000

Data Index: 730269 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3018. Min Act: -0.0000

Data Index: 236568 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1020635 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1328398 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2810. Min Act: -0.0001

Data Index: 941068 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2902. Min Act: -0.0001

Data Index: 36430 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2683. Min Act: -0.0000

Data Index: 293114 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1155998 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2869. Min Act: -0.0000

Data Index: 421462 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2769. Min Act: -0.0000

Data Index: 772502 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2736. Min Act: -0.0001

Data Index: 458081 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2628. Min Act: -0.0000

Data Index: 82751 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2637. Min Act: -0.0001

Data Index: 273947 (C4 (Web Text))

Max Activating Token Index: 387