Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.3244. Min Act: -0.0000

Data Index: 780992 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.3495. Min Act: -0.0000

Data Index: 592998 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.2497. Min Act: -0.0000

Data Index: 290291 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.3569. Min Act: -0.0000

Data Index: 502662 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.3489. Min Act: -0.0000

Data Index: 632633 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.1945. Min Act: -0.0000

Data Index: 742037 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.1764. Min Act: -0.0000

Data Index: 228771 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 2.3569. Min Range: -2.3569

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1148995 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1259373 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.2140. Min Act: -0.0000

Data Index: 418458 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.0936. Min Act: -0.0000

Data Index: 498793 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.0791. Min Act: -0.0000

Data Index: 224317 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.0626. Min Act: -0.0000

Data Index: 151021 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.0376. Min Act: -0.0000

Data Index: 809499 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.0363. Min Act: -0.0000

Data Index: 90784 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 2.3569. Min Range: -2.3569

Max Act: 1.8837. Min Act: -0.0000

Data Index: 272132 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.1041. Min Act: -0.0000

Data Index: 17439 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.1052. Min Act: -0.0000

Data Index: 610215 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 2.3569. Min Range: -2.3569

Max Act: 2.0936. Min Act: -0.0000

Data Index: 810690 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 2.3569. Min Range: -2.3569

Max Act: 1.9689. Min Act: -0.0000

Data Index: 1068887 (C4 (Web Text))

Max Activating Token Index: 662