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

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

Neuron 3164 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: 0.6186. Min Range: -0.6186

Max Act: 0.6186. Min Act: -0.0001

Data Index: 582913 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.6132. Min Act: -0.0001

Data Index: 16176 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5145. Min Act: -0.0001

Data Index: 755195 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1322387 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5610. Min Act: -0.0000

Data Index: 95614 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5435. Min Act: -0.0001

Data Index: 869196 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5318. Min Act: -0.0001

Data Index: 697214 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5195. Min Act: -0.0001

Data Index: 554623 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5692. Min Act: -0.0001

Data Index: 247001 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5077. Min Act: -0.0001

Data Index: 579412 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5070. Min Act: -0.0000

Data Index: 260703 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1162738 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4771. Min Act: -0.0001

Data Index: 527296 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4545. Min Act: -0.0000

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4946. Min Act: -0.0001

Data Index: 580405 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4608. Min Act: -0.0001

Data Index: 868689 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4547. Min Act: -0.0000

Data Index: 533176 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4507. Min Act: -0.0001

Data Index: 313507 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4634. Min Act: -0.0001

Data Index: 887579 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 505