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

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

Neuron 1548 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1333666 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2670. Min Act: -0.0000

Data Index: 400156 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1179916 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2583. Min Act: -0.0000

Data Index: 505203 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2530. Min Act: -0.0000

Data Index: 642349 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2268. Min Act: -0.0001

Data Index: 5676 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1284100 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2211. Min Act: -0.0001

Data Index: 51545 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2086. Min Act: -0.0001

Data Index: 701361 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1966. Min Act: -0.0000

Data Index: 642999 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1020314 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1835. Min Act: -0.0000

Data Index: 531969 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1858. Min Act: -0.0000

Data Index: 543075 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1991. Min Act: -0.0000

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1933. Min Act: -0.0000

Data Index: 773217 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1945. Min Act: -0.0000

Data Index: 64332 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1873. Min Act: -0.0001

Data Index: 366437 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1862. Min Act: -0.0001

Data Index: 638435 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1206078 (C4 (Web Text))

Max Activating Token Index: 26