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

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

Neuron 1748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.8107. Min Act: -0.0001

Data Index: 1268599 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6158. Min Act: -0.0001

Data Index: 204184 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.7617. Min Act: -0.0001

Data Index: 639682 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.7122. Min Act: -0.0001

Data Index: 109623 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.7302. Min Act: -0.0002

Data Index: 751333 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6165. Min Act: -0.0001

Data Index: 513599 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6796. Min Act: -0.0001

Data Index: 1356385 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6775. Min Act: -0.0001

Data Index: 291839 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6740. Min Act: -0.0001

Data Index: 632492 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5381. Min Act: -0.0001

Data Index: 724860 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6293. Min Act: -0.0001

Data Index: 1280889 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6837. Min Act: -0.0001

Data Index: 1179754 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6409. Min Act: -0.0001

Data Index: 735340 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5466. Min Act: -0.0001

Data Index: 552570 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5730. Min Act: -0.0001

Data Index: 261869 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5962. Min Act: -0.0001

Data Index: 192345 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.6136. Min Act: -0.0001

Data Index: 660575 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5717. Min Act: -0.0001

Data Index: 992513 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5029. Min Act: -0.0001

Data Index: 89394 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.8107. Min Range: -0.8107

Max Act: 0.5738. Min Act: -0.0001

Data Index: 52101 (C4 (Web Text))

Max Activating Token Index: 83