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

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

Neuron 5579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.5970. Min Act: -0.0000

Data Index: 1056269 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.1134. Min Act: -0.0000

Data Index: 857336 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0656. Min Act: -0.0000

Data Index: 1317165 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0519. Min Act: -0.0000

Data Index: 763203 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0830. Min Act: -0.0000

Data Index: 240346 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0470. Min Act: -0.0000

Data Index: 659035 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0608. Min Act: -0.0000

Data Index: 845633 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.9469. Min Act: -0.0000

Data Index: 1158000 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.9232. Min Act: -0.0000

Data Index: 958307 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.9409. Min Act: -0.0000

Data Index: 904368 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0438. Min Act: -0.0000

Data Index: 922365 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0436. Min Act: -0.0000

Data Index: 620543 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.8943. Min Act: -0.0000

Data Index: 577758 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.1100. Min Act: -0.0000

Data Index: 426938 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.8662. Min Act: -0.0000

Data Index: 1215103 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1097852 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.9714. Min Act: -0.0000

Data Index: 804739 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.9692. Min Act: -0.0000

Data Index: 247299 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 2.5970. Min Range: -2.5970

Max Act: 2.0728. Min Act: -0.0000

Data Index: 392193 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 2.5970. Min Range: -2.5970

Max Act: 1.9621. Min Act: -0.0000

Data Index: 217046 (C4 (Web Text))

Max Activating Token Index: 446