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

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

Neuron 3318 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: 0.5583. Min Range: -0.5583

Max Act: 0.5583. Min Act: -0.0000

Data Index: 555070 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1353473 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4589. Min Act: -0.0000

Data Index: 294527 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1009540 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3881. Min Act: -0.0000

Data Index: 143752 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1147879 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4146. Min Act: -0.0000

Data Index: 860187 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1116713 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3544. Min Act: -0.0001

Data Index: 362683 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1322628 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4067. Min Act: -0.0000

Data Index: 16681 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3776. Min Act: -0.0001

Data Index: 149441 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3903. Min Act: -0.0000

Data Index: 980652 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3814. Min Act: -0.0000

Data Index: 592251 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3965. Min Act: -0.0000

Data Index: 537054 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3804. Min Act: -0.0000

Data Index: 136175 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1297422 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1341150 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4032. Min Act: -0.0000

Data Index: 455354 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.3604. Min Act: -0.0001

Data Index: 1216034 (C4 (Web Text))

Max Activating Token Index: 664