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

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

Neuron 2118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.6464. Min Act: -0.0000

Data Index: 1298387 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.5046. Min Act: -0.0000

Data Index: 1187185 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.6354. Min Act: -0.0000

Data Index: 148054 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.2495. Min Act: -0.0000

Data Index: 418512 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.4024. Min Act: -0.0000

Data Index: 447952 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.0578. Min Act: -0.0000

Data Index: 307585 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.1309. Min Act: -0.0000

Data Index: 818245 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.0654. Min Act: -0.0000

Data Index: 1345658 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.0433. Min Act: -0.0000

Data Index: 948090 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.9504. Min Act: -0.0000

Data Index: 606980 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.0433. Min Act: -0.0000

Data Index: 1113647 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.8204. Min Act: -0.0000

Data Index: 1301940 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.3499. Min Act: -0.0000

Data Index: 108790 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 2.6464. Min Range: -2.6464

Max Act: 2.0057. Min Act: -0.0000

Data Index: 944645 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1081857 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.8742. Min Act: -0.0000

Data Index: 330647 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.8604. Min Act: -0.0000

Data Index: 282665 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.7549. Min Act: -0.0000

Data Index: 671828 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.7404. Min Act: -0.0000

Data Index: 378521 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 2.6464. Min Range: -2.6464

Max Act: 1.8159. Min Act: -0.0000

Data Index: 525115 (C4 (Web Text))

Max Activating Token Index: 21