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

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

Neuron 1356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.1978. Min Act: -0.0001

Data Index: 664899 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.0932. Min Act: -0.0000

Data Index: 83924 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.2740. Min Act: -0.0000

Data Index: 1174076 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.1287. Min Act: -0.0001

Data Index: 4373 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1346392 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.0575. Min Act: -0.0000

Data Index: 426758 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9583. Min Act: -0.0001

Data Index: 634970 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1030648 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9647. Min Act: -0.0000

Data Index: 57331 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1223078 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1103382 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9525. Min Act: -0.0000

Data Index: 308260 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.8342. Min Act: -0.0000

Data Index: 729869 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1141663 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9479. Min Act: -0.0000

Data Index: 1044020 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.2740. Min Range: -1.2740

Max Act: 1.0121. Min Act: -0.0000

Data Index: 173663 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9109. Min Act: -0.0000

Data Index: 74145 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.7524. Min Act: -0.0000

Data Index: 339834 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.9244. Min Act: -0.0000

Data Index: 804393 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.2740. Min Range: -1.2740

Max Act: 0.8337. Min Act: -0.0000

Data Index: 441211 (C4 (Web Text))

Max Activating Token Index: 702