Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2180 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.5118. Min Act: -0.0000

Data Index: 611063 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.3833. Min Act: -0.0000

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2408. Min Act: 0.0000

Data Index: 935638 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1119379 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2125. Min Act: -0.0000

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1491. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1714. Min Act: -0.0001

Data Index: 1503919 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1447. Min Act: -0.0000

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1559. Min Act: -0.0001

Data Index: 1553450 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1815. Min Act: -0.0001

Data Index: 156008 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1127697 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1423. Min Act: -0.0001

Data Index: 1569920 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1493686 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.0148. Min Act: -0.0001

Data Index: 254380 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.0112. Min Act: -0.0001

Data Index: 351254 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.0025. Min Act: -0.0001

Data Index: 1535035 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.0587. Min Act: -0.0000

Data Index: 260788 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.5118. Min Range: -1.5118

Max Act: 0.9592. Min Act: -0.0000

Data Index: 287315 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.5118. Min Range: -1.5118

Max Act: 0.9875. Min Act: -0.0001

Data Index: 484188 (C4 (Web Text))

Max Activating Token Index: 373