Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4893. Min Act: -0.0001

Data Index: 125977 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4758. Min Act: -0.0001

Data Index: 1152431 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4462. Min Act: -0.0001

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4630. Min Act: -0.0001

Data Index: 147372 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3990. Min Act: -0.0001

Data Index: 1071936 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3937. Min Act: -0.0001

Data Index: 902070 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3972. Min Act: -0.0001

Data Index: 456086 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3943. Min Act: -0.0001

Data Index: 289514 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3761. Min Act: -0.0001

Data Index: 625053 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3596. Min Act: -0.0001

Data Index: 533571 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3806. Min Act: -0.0001

Data Index: 927447 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3551. Min Act: -0.0001

Data Index: 418237 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3748. Min Act: -0.0001

Data Index: 162350 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3701. Min Act: -0.0001

Data Index: 644164 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3349. Min Act: -0.0001

Data Index: 200072 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3713. Min Act: -0.0001

Data Index: 238179 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4021. Min Act: -0.0001

Data Index: 913506 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3499. Min Act: -0.0001

Data Index: 658608 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3979. Min Act: -0.0001

Data Index: 512700 (C4 (Web Text))

Max Activating Token Index: 147