Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4070 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3435. Min Range: -2.3435

Max Act: 2.3435. Min Act: -0.0000

Data Index: 1323847 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.9973. Min Act: -0.0000

Data Index: 493098 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.7839. Min Act: -0.0000

Data Index: 982922 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.7566. Min Act: -0.0000

Data Index: 1343288 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.5713. Min Act: -0.0000

Data Index: 982571 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.6393. Min Act: -0.0000

Data Index: 1138787 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.7065. Min Act: -0.0000

Data Index: 392275 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4184. Min Act: -0.0000

Data Index: 798515 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.5743. Min Act: -0.0000

Data Index: 184955 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4760. Min Act: -0.0000

Data Index: 220006 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1002873 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.3642. Min Act: -0.0000

Data Index: 812009 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.3580. Min Act: -0.0000

Data Index: 312585 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4017. Min Act: -0.0000

Data Index: 689799 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.3899. Min Act: -0.0000

Data Index: 1272266 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1177354 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.3095. Min Act: -0.0000

Data Index: 448422 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4592. Min Act: -0.0000

Data Index: 929646 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.4465. Min Act: -0.0000

Data Index: 414056 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 2.3435. Min Range: -2.3435

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1105382 (C4 (Web Text))

Max Activating Token Index: 632