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

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

Neuron 3158 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: 0.4276. Min Range: -0.4276

Max Act: 0.4276. Min Act: -0.0001

Data Index: 186261 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3933. Min Act: -0.0000

Data Index: 172757 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1036639 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3181. Min Act: -0.0001

Data Index: 571736 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3307. Min Act: -0.0001

Data Index: 484810 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3415. Min Act: -0.0001

Data Index: 591271 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1276590 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1064725 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2961. Min Act: -0.0000

Data Index: 378745 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2731. Min Act: -0.0001

Data Index: 629275 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2839. Min Act: -0.0000

Data Index: 442582 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2924. Min Act: -0.0001

Data Index: 994308 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2804. Min Act: -0.0000

Data Index: 695658 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.3052. Min Act: -0.0001

Data Index: 993937 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2956. Min Act: -0.0000

Data Index: 752707 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2668. Min Act: -0.0001

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1297570 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2660. Min Act: -0.0000

Data Index: 955938 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1253638 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.4276. Min Range: -0.4276

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1182702 (C4 (Web Text))

Max Activating Token Index: 712