Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2046 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.3004. Min Act: -0.0001

Data Index: 1148769 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1110192 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2666. Min Act: -0.0001

Data Index: 912460 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2462. Min Act: -0.0001

Data Index: 809833 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2442. Min Act: -0.0001

Data Index: 107923 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2344. Min Act: -0.0001

Data Index: 741115 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2415. Min Act: -0.0001

Data Index: 96631 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2327. Min Act: -0.0001

Data Index: 449669 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2456. Min Act: -0.0001

Data Index: 795914 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2323. Min Act: -0.0001

Data Index: 352914 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2145. Min Act: -0.0001

Data Index: 132256 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1275264 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2223. Min Act: -0.0001

Data Index: 617811 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2227. Min Act: -0.0001

Data Index: 21669 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2174. Min Act: -0.0001

Data Index: 732315 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.1976. Min Act: -0.0001

Data Index: 954837 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2263. Min Act: -0.0001

Data Index: 209579 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2076. Min Act: -0.0001

Data Index: 381470 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2317. Min Act: -0.0001

Data Index: 966078 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2155. Min Act: -0.0001

Data Index: 283809 (C4 (Web Text))

Max Activating Token Index: 325