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

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

Neuron 900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0699. Min Range: -1.0699

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1632610 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7656. Min Act: -0.0000

Data Index: 866508 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.7482. Min Act: -0.0000

Data Index: 535056 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6874. Min Act: -0.0000

Data Index: 50322 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.6366. Min Act: -0.0000

Data Index: 771504 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1173971 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5695. Min Act: -0.0000

Data Index: 590066 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1155596 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1208591 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5797. Min Act: -0.0000

Data Index: 861979 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5443. Min Act: -0.0000

Data Index: 974726 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5059. Min Act: -0.0000

Data Index: 377997 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1222261 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5332. Min Act: -0.0000

Data Index: 619515 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.4969. Min Act: -0.0000

Data Index: 862272 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1390713 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.5950. Min Act: -0.0000

Data Index: 833104 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.4636. Min Act: -0.0000

Data Index: 33854 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.4180. Min Act: -0.0000

Data Index: 258290 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.0699. Min Range: -1.0699

Max Act: 0.4967. Min Act: -0.0000

Data Index: 514329 (C4 (Web Text))

Max Activating Token Index: 469