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

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

Neuron 1916 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: 0.5939. Min Range: -0.5939

Max Act: 0.5939. Min Act: -0.0001

Data Index: 1053514 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5700. Min Act: -0.0000

Data Index: 260624 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5465. Min Act: -0.0000

Data Index: 818894 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5588. Min Act: -0.0001

Data Index: 168046 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5287. Min Act: -0.0000

Data Index: 555942 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5262. Min Act: -0.0000

Data Index: 921512 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5217. Min Act: -0.0001

Data Index: 871141 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5160. Min Act: -0.0000

Data Index: 398124 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5475. Min Act: -0.0001

Data Index: 583641 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4927. Min Act: -0.0000

Data Index: 628540 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5084. Min Act: -0.0000

Data Index: 838506 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4893. Min Act: -0.0000

Data Index: 268077 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5372. Min Act: -0.0001

Data Index: 248008 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1264043 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1330928 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4763. Min Act: -0.0001

Data Index: 815685 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4623. Min Act: -0.0001

Data Index: 217766 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1259840 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4676. Min Act: -0.0001

Data Index: 987130 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5004. Min Act: -0.0001

Data Index: 996015 (C4 (Web Text))

Max Activating Token Index: 46