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

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

Neuron 670 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: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0001

Data Index: 1064708 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3478. Min Act: -0.0000

Data Index: 712103 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1346280 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3148. Min Act: -0.0001

Data Index: 708455 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3210. Min Act: -0.0001

Data Index: 266866 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3176. Min Act: -0.0001

Data Index: 424377 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3077. Min Act: -0.0001

Data Index: 829249 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3009. Min Act: -0.0001

Data Index: 990010 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2983. Min Act: -0.0001

Data Index: 1288976 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2975. Min Act: -0.0000

Data Index: 709896 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3048. Min Act: -0.0001

Data Index: 841791 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3078. Min Act: -0.0001

Data Index: 826904 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2809. Min Act: -0.0001

Data Index: 31123 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1215816 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2926. Min Act: -0.0000

Data Index: 417574 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1145483 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2709. Min Act: -0.0000

Data Index: 284781 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2778. Min Act: -0.0001

Data Index: 874105 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2756. Min Act: -0.0000

Data Index: 984971 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1286007 (C4 (Web Text))

Max Activating Token Index: 439