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

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

Neuron 15 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.3105. Min Act: -0.0001

Data Index: 669617 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1020514 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1285460 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2755. Min Act: -0.0001

Data Index: 1331003 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2581. Min Act: -0.0001

Data Index: 742679 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1226216 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2351. Min Act: -0.0001

Data Index: 950079 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2315. Min Act: -0.0001

Data Index: 137379 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2241. Min Act: -0.0001

Data Index: 474234 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2135. Min Act: -0.0001

Data Index: 175411 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1026148 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2216. Min Act: -0.0001

Data Index: 669050 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1022624 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1083931 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2032. Min Act: -0.0001

Data Index: 349368 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2080. Min Act: -0.0001

Data Index: 949440 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2316. Min Act: -0.0001

Data Index: 597249 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2093. Min Act: -0.0001

Data Index: 115468 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1031555 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2126. Min Act: -0.0001

Data Index: 825134 (C4 (Web Text))

Max Activating Token Index: 470