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

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

Neuron 260 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0061. Min Range: -7.0061

Max Act: 7.0061. Min Act: -0.0000

Data Index: 1144461 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.9967. Min Act: -0.0000

Data Index: 1215287 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.7409. Min Act: -0.0000

Data Index: 299745 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 7.0061. Min Range: -7.0061

Max Act: 6.1044. Min Act: -0.0000

Data Index: 776523 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.7453. Min Act: -0.0000

Data Index: 1234245 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.8899. Min Act: -0.0000

Data Index: 808169 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.8650. Min Act: -0.0000

Data Index: 237411 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 7.0061. Min Range: -7.0061

Max Act: 6.0166. Min Act: -0.0000

Data Index: 31570 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.3943. Min Act: -0.0000

Data Index: 851826 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.8850. Min Act: -0.0000

Data Index: 1261503 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.7235. Min Act: -0.0000

Data Index: 846485 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.5087. Min Act: -0.0000

Data Index: 795953 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.8204. Min Act: -0.0000

Data Index: 445487 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.7568. Min Act: -0.0000

Data Index: 275118 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.4596. Min Act: -0.0000

Data Index: 1212339 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.6143. Min Act: -0.0000

Data Index: 1194340 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.7160. Min Act: -0.0000

Data Index: 1020446 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.5380. Min Act: -0.0000

Data Index: 413125 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 7.0061. Min Range: -7.0061

Max Act: 5.3181. Min Act: -0.0000

Data Index: 537 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.8704. Min Act: -0.0000

Data Index: 291853 (C4 (Web Text))

Max Activating Token Index: 831