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

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

Neuron 907 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: 0.4112. Min Range: -0.4112

Max Act: 0.4112. Min Act: -0.0000

Data Index: 192872 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1263591 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3186. Min Act: -0.0000

Data Index: 495793 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1183778 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2993. Min Act: -0.0000

Data Index: 540083 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.3199. Min Act: -0.0001

Data Index: 1258728 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2856. Min Act: -0.0000

Data Index: 514088 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2742. Min Act: -0.0000

Data Index: 48077 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2805. Min Act: -0.0000

Data Index: 359431 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2818. Min Act: -0.0000

Data Index: 560565 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2753. Min Act: -0.0000

Data Index: 485661 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2736. Min Act: -0.0000

Data Index: 729237 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2535. Min Act: -0.0000

Data Index: 249636 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1002782 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2779. Min Act: -0.0000

Data Index: 245600 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2562. Min Act: -0.0000

Data Index: 248811 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2647. Min Act: -0.0000

Data Index: 103791 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2635. Min Act: -0.0000

Data Index: 441297 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2522. Min Act: -0.0000

Data Index: 171381 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.4112. Min Range: -0.4112

Max Act: 0.2627. Min Act: -0.0001

Data Index: 102651 (C4 (Web Text))

Max Activating Token Index: 323