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

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

Neuron 4552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.3951. Min Act: -0.0000

Data Index: 30898 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7033. Min Act: -0.0000

Data Index: 538786 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.0136. Min Act: -0.0000

Data Index: 299169 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.0349. Min Act: -0.0000

Data Index: 1018742 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 4.3951. Min Range: -4.3951

Max Act: 4.1592. Min Act: -0.0001

Data Index: 257723 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.9206. Min Act: -0.0000

Data Index: 386836 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7214. Min Act: -0.0000

Data Index: 764117 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7160. Min Act: -0.0000

Data Index: 515015 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.8435. Min Act: -0.0000

Data Index: 603748 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.8500. Min Act: -0.0000

Data Index: 512249 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.6921. Min Act: -0.0000

Data Index: 648103 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.8074. Min Act: -0.0000

Data Index: 372695 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.8022. Min Act: -0.0000

Data Index: 552571 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.6043. Min Act: -0.0000

Data Index: 118765 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.6068. Min Act: -0.0000

Data Index: 195590 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7539. Min Act: -0.0000

Data Index: 432943 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7536. Min Act: -0.0000

Data Index: 801960 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7579. Min Act: -0.0000

Data Index: 916570 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.5754. Min Act: -0.0000

Data Index: 17700 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 4.3951. Min Range: -4.3951

Max Act: 3.7050. Min Act: -0.0000

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 394