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

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

Neuron 614 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3872. Min Range: -3.3872

Max Act: 3.3872. Min Act: -0.0000

Data Index: 395579 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1291028 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.6235. Min Act: -0.0001

Data Index: 81977 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.4923. Min Act: -0.0000

Data Index: 892321 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.2302. Min Act: -0.0001

Data Index: 693970 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.2866. Min Act: -0.0000

Data Index: 297800 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.0362. Min Act: -0.0000

Data Index: 1022582 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.1570. Min Act: -0.0001

Data Index: 1106987 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.3872. Min Range: -3.3872

Max Act: 2.0038. Min Act: -0.0000

Data Index: 136431 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.9081. Min Act: -0.0001

Data Index: 44020 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.5623. Min Act: -0.0000

Data Index: 1312413 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.5091. Min Act: -0.0000

Data Index: 1076436 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.4867. Min Act: -0.0001

Data Index: 919391 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.4245. Min Act: -0.0001

Data Index: 1047192 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.3275. Min Act: -0.0001

Data Index: 1312167 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.3390. Min Act: -0.0000

Data Index: 893958 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.2648. Min Act: -0.0000

Data Index: 23758 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.1493. Min Act: -0.0000

Data Index: 217497 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.1912. Min Act: -0.0001

Data Index: 612464 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 3.3872. Min Range: -3.3872

Max Act: 1.1867. Min Act: -0.0000

Data Index: 340844 (C4 (Web Text))

Max Activating Token Index: 844