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

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

Neuron 2202 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6159. Min Range: -3.6159

Max Act: 3.6159. Min Act: -0.0001

Data Index: 890037 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 3.6159. Min Range: -3.6159

Max Act: 3.4505. Min Act: -0.0001

Data Index: 1250351 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.6159. Min Range: -3.6159

Max Act: 3.2708. Min Act: -0.0001

Data Index: 983745 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.9173. Min Act: -0.0001

Data Index: 1150622 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 3.6159. Min Range: -3.6159

Max Act: 3.0468. Min Act: -0.0001

Data Index: 442661 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.8846. Min Act: -0.0001

Data Index: 179882 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.9233. Min Act: -0.0000

Data Index: 299001 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.8825. Min Act: -0.0000

Data Index: 1114785 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.8265. Min Act: -0.0001

Data Index: 1178983 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.6137. Min Act: -0.0001

Data Index: 679343 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.5754. Min Act: -0.0000

Data Index: 460586 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.6580. Min Act: -0.0001

Data Index: 991347 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.6652. Min Act: -0.0001

Data Index: 594380 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.7789. Min Act: -0.0001

Data Index: 495218 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.9305. Min Act: -0.0000

Data Index: 1146588 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.4517. Min Act: -0.0001

Data Index: 597291 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.5692. Min Act: -0.0000

Data Index: 132091 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.4988. Min Act: -0.0001

Data Index: 973731 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.6193. Min Act: -0.0001

Data Index: 271263 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 3.6159. Min Range: -3.6159

Max Act: 2.3547. Min Act: -0.0001

Data Index: 1015524 (C4 (Web Text))

Max Activating Token Index: 529