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

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

Neuron 3579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1006889 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2935. Min Act: -0.0000

Data Index: 29813 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2810. Min Act: -0.0000

Data Index: 644443 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2860. Min Act: -0.0000

Data Index: 487949 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2831. Min Act: -0.0000

Data Index: 264135 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2740. Min Act: -0.0000

Data Index: 298517 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2735. Min Act: -0.0000

Data Index: 26252 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2734. Min Act: -0.0000

Data Index: 630715 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1140878 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2506. Min Act: -0.0000

Data Index: 928490 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2577. Min Act: -0.0000

Data Index: 170262 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2460. Min Act: -0.0000

Data Index: 551394 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2453. Min Act: -0.0000

Data Index: 276753 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1337933 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2471. Min Act: -0.0000

Data Index: 520053 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2399. Min Act: -0.0000

Data Index: 635517 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2459. Min Act: -0.0000

Data Index: 312295 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1147847 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2331. Min Act: -0.0000

Data Index: 767200 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.3560. Min Range: -0.3560

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1283687 (C4 (Web Text))

Max Activating Token Index: 398