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

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

Neuron 4561 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3842. Min Act: -0.0000

Data Index: 795561 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3685. Min Act: -0.0000

Data Index: 524003 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3137. Min Act: -0.0000

Data Index: 190124 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2987. Min Act: -0.0000

Data Index: 117225 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1022170 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2946. Min Act: -0.0000

Data Index: 954946 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1161921 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1101394 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2696. Min Act: -0.0000

Data Index: 399755 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2540. Min Act: -0.0000

Data Index: 76731 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2784. Min Act: -0.0000

Data Index: 394354 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2670. Min Act: -0.0000

Data Index: 465938 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1135397 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2618. Min Act: -0.0000

Data Index: 919319 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2622. Min Act: -0.0000

Data Index: 149217 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2546. Min Act: -0.0000

Data Index: 393217 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1145088 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2388. Min Act: -0.0000

Data Index: 698775 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2416. Min Act: -0.0000

Data Index: 604532 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.3842. Min Range: -0.3842

Max Act: 0.2562. Min Act: -0.0000

Data Index: 987003 (C4 (Web Text))

Max Activating Token Index: 210