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

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

Neuron 2736 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: 0.4820. Min Range: -0.4820

Max Act: 0.4820. Min Act: -0.0001

Data Index: 386487 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1182730 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1053223 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3686. Min Act: -0.0001

Data Index: 219302 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3570. Min Act: -0.0001

Data Index: 1320545 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3404. Min Act: -0.0001

Data Index: 429336 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1125830 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3554. Min Act: -0.0001

Data Index: 759960 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3474. Min Act: -0.0001

Data Index: 771676 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3508. Min Act: -0.0001

Data Index: 609680 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3485. Min Act: -0.0001

Data Index: 81969 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1055191 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3597. Min Act: -0.0001

Data Index: 852260 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3431. Min Act: -0.0001

Data Index: 1355700 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1151303 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3528. Min Act: -0.0001

Data Index: 1042214 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1218956 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3090. Min Act: -0.0001

Data Index: 427145 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3351. Min Act: -0.0001

Data Index: 561121 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3244. Min Act: -0.0001

Data Index: 331814 (C4 (Web Text))

Max Activating Token Index: 404