Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 140 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9666. Min Act: -0.0000

Data Index: 206500 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8932. Min Act: -0.0000

Data Index: 95961 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9404. Min Act: -0.0001

Data Index: 578023 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8418. Min Act: -0.0000

Data Index: 96183 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8129. Min Act: -0.0001

Data Index: 724290 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7444. Min Act: -0.0000

Data Index: 4163 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7539. Min Act: -0.0001

Data Index: 1009513 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6947. Min Act: -0.0001

Data Index: 1226049 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7369. Min Act: -0.0001

Data Index: 20999 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1014427 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7328. Min Act: -0.0001

Data Index: 111104 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6835. Min Act: -0.0000

Data Index: 497494 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7043. Min Act: -0.0001

Data Index: 1028954 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6588. Min Act: -0.0000

Data Index: 327713 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6509. Min Act: -0.0000

Data Index: 488008 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6073. Min Act: -0.0001

Data Index: 503169 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6470. Min Act: -0.0001

Data Index: 717293 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6550. Min Act: -0.0001

Data Index: 143664 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1229875 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.6098. Min Act: -0.0000

Data Index: 475449 (C4 (Web Text))

Max Activating Token Index: 800