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

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

Neuron 4122 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: 0.9463. Min Range: -0.9463

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1166200 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1314212 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8636. Min Act: -0.0000

Data Index: 283609 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8461. Min Act: -0.0000

Data Index: 394754 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8271. Min Act: -0.0000

Data Index: 158177 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7553. Min Act: -0.0000

Data Index: 913408 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7084. Min Act: -0.0000

Data Index: 23816 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7260. Min Act: -0.0000

Data Index: 69941 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1070107 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1182615 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7089. Min Act: -0.0000

Data Index: 574971 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7305. Min Act: -0.0000

Data Index: 825049 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6643. Min Act: -0.0000

Data Index: 96291 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6450. Min Act: -0.0000

Data Index: 476141 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6432. Min Act: -0.0000

Data Index: 352111 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6425. Min Act: -0.0000

Data Index: 869703 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6462. Min Act: -0.0000

Data Index: 999667 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1173667 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6499. Min Act: -0.0000

Data Index: 540094 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.6488. Min Act: -0.0000

Data Index: 937003 (C4 (Web Text))

Max Activating Token Index: 281