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

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

Neuron 2157 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1195973 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3905. Min Act: 0.0000

Data Index: 913129 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1143521 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.4044. Min Act: -0.0000

Data Index: 893666 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3845. Min Act: -0.0000

Data Index: 610395 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3747. Min Act: -0.0000

Data Index: 518894 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3727. Min Act: -0.0000

Data Index: 77414 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3576. Min Act: -0.0000

Data Index: 344627 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3660. Min Act: -0.0001

Data Index: 1113512 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3559. Min Act: -0.0000

Data Index: 751827 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3547. Min Act: -0.0000

Data Index: 574545 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3521. Min Act: -0.0000

Data Index: 391243 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3633. Min Act: -0.0000

Data Index: 904503 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3402. Min Act: -0.0000

Data Index: 309996 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3485. Min Act: -0.0000

Data Index: 146150 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3367. Min Act: -0.0000

Data Index: 137883 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1148644 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3537. Min Act: -0.0000

Data Index: 121392 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3258. Min Act: -0.0001

Data Index: 72985 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1095077 (C4 (Web Text))

Max Activating Token Index: 262