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

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

Neuron 553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.8276. Min Act: -0.0001

Data Index: 480791 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0001

Data Index: 594627 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7066. Min Act: -0.0001

Data Index: 240451 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7293. Min Act: -0.0001

Data Index: 1015320 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7024. Min Act: -0.0000

Data Index: 601762 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6968. Min Act: -0.0000

Data Index: 834332 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7021. Min Act: -0.0001

Data Index: 735460 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6873. Min Act: -0.0000

Data Index: 352864 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6591. Min Act: -0.0000

Data Index: 320922 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1158989 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6602. Min Act: -0.0001

Data Index: 291280 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6520. Min Act: -0.0001

Data Index: 62192 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6064. Min Act: -0.0000

Data Index: 793444 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6454. Min Act: -0.0001

Data Index: 906551 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6233. Min Act: -0.0000

Data Index: 994863 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6175. Min Act: -0.0001

Data Index: 675831 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1180638 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1248195 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5989. Min Act: -0.0001

Data Index: 806376 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5930. Min Act: -0.0001

Data Index: 982739 (C4 (Web Text))

Max Activating Token Index: 966