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

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

Neuron 3494 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3575. Min Act: -0.0001

Data Index: 1233341 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3291. Min Act: -0.0001

Data Index: 309914 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3649. Min Act: -0.0001

Data Index: 561817 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1296644 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3358. Min Act: -0.0001

Data Index: 269653 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3520. Min Act: -0.0001

Data Index: 427968 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3596. Min Act: -0.0001

Data Index: 848144 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3460. Min Act: -0.0001

Data Index: 1148053 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3262. Min Act: -0.0001

Data Index: 244275 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3700. Min Act: -0.0001

Data Index: 897515 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3562. Min Act: -0.0001

Data Index: 435048 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3643. Min Act: -0.0001

Data Index: 373370 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3477. Min Act: -0.0001

Data Index: 884875 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3497. Min Act: -0.0001

Data Index: 64380 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3336. Min Act: -0.0001

Data Index: 123638 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3438. Min Act: -0.0001

Data Index: 326035 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3542. Min Act: -0.0001

Data Index: 619055 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3310. Min Act: -0.0001

Data Index: 206013 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3214. Min Act: -0.0001

Data Index: 675746 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3348. Min Act: -0.0001

Data Index: 587113 (C4 (Web Text))

Max Activating Token Index: 329