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

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

Neuron 2958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.3586. Min Act: -0.0000

Data Index: 20942 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1220285 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.3280. Min Act: -0.0001

Data Index: 501327 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.3263. Min Act: -0.0000

Data Index: 297832 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.3061. Min Act: -0.0001

Data Index: 6782 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.3050. Min Act: -0.0001

Data Index: 939791 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1150948 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2827. Min Act: -0.0000

Data Index: 179190 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2907. Min Act: -0.0000

Data Index: 906283 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2892. Min Act: -0.0000

Data Index: 639299 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1109220 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2867. Min Act: -0.0000

Data Index: 82511 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2950. Min Act: -0.0000

Data Index: 620728 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2756. Min Act: -0.0000

Data Index: 925563 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2832. Min Act: -0.0000

Data Index: 402103 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2939. Min Act: -0.0000

Data Index: 894629 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2641. Min Act: -0.0000

Data Index: 97733 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1100304 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2649. Min Act: -0.0001

Data Index: 576009 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.3586. Min Range: -0.3586

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1032730 (C4 (Web Text))

Max Activating Token Index: 466