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

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

Neuron 2005 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: 1.0236. Min Range: -1.0236

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1309980 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9462. Min Act: -0.0000

Data Index: 638542 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8392. Min Act: -0.0000

Data Index: 723415 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7702. Min Act: 0.0000

Data Index: 727947 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6539. Min Act: -0.0000

Data Index: 32386 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1017370 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1299663 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1214101 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6206. Min Act: -0.0000

Data Index: 103222 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6096. Min Act: -0.0000

Data Index: 732952 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.6038. Min Act: -0.0000

Data Index: 225091 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5565. Min Act: -0.0000

Data Index: 511167 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5825. Min Act: -0.0000

Data Index: 34097 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5797. Min Act: -0.0000

Data Index: 165327 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5688. Min Act: -0.0000

Data Index: 690832 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5393. Min Act: -0.0000

Data Index: 949964 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5981. Min Act: -0.0000

Data Index: 272775 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5605. Min Act: -0.0000

Data Index: 562901 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5592. Min Act: -0.0000

Data Index: 833644 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.5378. Min Act: -0.0000

Data Index: 861703 (C4 (Web Text))

Max Activating Token Index: 755