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

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

Neuron 30 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0000

Data Index: 61970 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4095. Min Act: -0.0000

Data Index: 690527 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1179012 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3795. Min Act: -0.0000

Data Index: 939942 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3328. Min Act: -0.0000

Data Index: 25465 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3070. Min Act: -0.0000

Data Index: 551567 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3172. Min Act: -0.0000

Data Index: 758860 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3121. Min Act: -0.0000

Data Index: 132970 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3157. Min Act: -0.0000

Data Index: 851826 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2851. Min Act: -0.0000

Data Index: 437104 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1145205 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1225534 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2881. Min Act: -0.0000

Data Index: 408789 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1130772 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3017. Min Act: -0.0000

Data Index: 724210 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2818. Min Act: -0.0000

Data Index: 591687 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1239277 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2844. Min Act: -0.0000

Data Index: 730445 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1190018 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.2835. Min Act: -0.0000

Data Index: 507578 (C4 (Web Text))

Max Activating Token Index: 481