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

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

Neuron 2270 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4288. Min Act: -0.0001

Data Index: 793250 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4001. Min Act: -0.0000

Data Index: 441348 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3902. Min Act: -0.0000

Data Index: 205896 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3969. Min Act: -0.0001

Data Index: 666700 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1289041 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1351784 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1124332 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3547. Min Act: -0.0001

Data Index: 590464 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3650. Min Act: -0.0001

Data Index: 765673 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3476. Min Act: -0.0000

Data Index: 535855 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3602. Min Act: -0.0000

Data Index: 250316 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1216507 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3823. Min Act: -0.0001

Data Index: 522857 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3652. Min Act: -0.0000

Data Index: 300479 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3520. Min Act: -0.0000

Data Index: 889083 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3381. Min Act: -0.0000

Data Index: 295009 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3471. Min Act: -0.0000

Data Index: 935026 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1074856 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3498. Min Act: -0.0001

Data Index: 916529 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3349. Min Act: -0.0001

Data Index: 777695 (C4 (Web Text))

Max Activating Token Index: 794