Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3947 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1027. Min Range: -6.1027

Max Act: 6.1027. Min Act: -0.0000

Data Index: 826698 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.8337. Min Act: -0.0000

Data Index: 1078887 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 6.1027. Min Range: -6.1027

Max Act: 6.0074. Min Act: -0.0000

Data Index: 592519 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.3858. Min Act: -0.0000

Data Index: 1059331 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.2356. Min Act: -0.0000

Data Index: 1073758 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.3910. Min Act: -0.0000

Data Index: 427040 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.3327. Min Act: -0.0000

Data Index: 65306 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.7410. Min Act: -0.0000

Data Index: 973663 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.5126. Min Act: -0.0000

Data Index: 417745 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.6787. Min Act: -0.0000

Data Index: 335221 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 6.1027. Min Range: -6.1027

Max Act: 5.6278. Min Act: -0.0000

Data Index: 1134640 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.9253. Min Act: -0.0000

Data Index: 648798 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.6347. Min Act: -0.0000

Data Index: 293203 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.6098. Min Act: -0.0000

Data Index: 1258806 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.7574. Min Act: -0.0000

Data Index: 351956 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.6668. Min Act: -0.0000

Data Index: 501473 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.6329. Min Act: -0.0000

Data Index: 853981 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.7816. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.5903. Min Act: -0.0000

Data Index: 1267825 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 6.1027. Min Range: -6.1027

Max Act: 4.5904. Min Act: -0.0000

Data Index: 1179731 (C4 (Web Text))

Max Activating Token Index: 166