Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 51 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1061286 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3214. Min Act: -0.0001

Data Index: 756645 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3089. Min Act: -0.0001

Data Index: 441004 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3084. Min Act: -0.0001

Data Index: 971421 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1175689 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2872. Min Act: -0.0001

Data Index: 170775 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2775. Min Act: -0.0001

Data Index: 179625 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1198031 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2489. Min Act: -0.0001

Data Index: 506448 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2508. Min Act: -0.0001

Data Index: 94587 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1226323 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2514. Min Act: -0.0001

Data Index: 103480 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2483. Min Act: -0.0001

Data Index: 45229 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2541. Min Act: -0.0001

Data Index: 26534 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2470. Min Act: -0.0001

Data Index: 687238 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2465. Min Act: -0.0001

Data Index: 320147 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2457. Min Act: -0.0001

Data Index: 376727 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2315. Min Act: -0.0001

Data Index: 423268 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2501. Min Act: -0.0001

Data Index: 818576 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1063455 (C4 (Web Text))

Max Activating Token Index: 389