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

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

Neuron 1611 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: 3.0108. Min Range: -3.0108

Max Act: 2.8907. Min Act: -0.0000

Data Index: 886140 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 3.0108. Min Range: -3.0108

Max Act: 3.0102. Min Act: -0.0000

Data Index: 492046 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.0108. Min Range: -3.0108

Max Act: 3.0108. Min Act: -0.0000

Data Index: 397646 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.8813. Min Act: -0.0000

Data Index: 989515 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6472. Min Act: -0.0000

Data Index: 1260719 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.9272. Min Act: -0.0000

Data Index: 1174449 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7589. Min Act: -0.0000

Data Index: 880394 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7353. Min Act: -0.0000

Data Index: 1316459 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.7242. Min Act: -0.0000

Data Index: 1027449 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6843. Min Act: -0.0000

Data Index: 950386 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.5175. Min Act: -0.0000

Data Index: 931529 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6222. Min Act: -0.0000

Data Index: 378432 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6227. Min Act: -0.0000

Data Index: 1233543 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.6038. Min Act: -0.0000

Data Index: 306050 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.5968. Min Act: -0.0000

Data Index: 279669 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.5937. Min Act: -0.0000

Data Index: 1254636 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.5682. Min Act: -0.0000

Data Index: 162911 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.5684. Min Act: -0.0000

Data Index: 91377 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.4331. Min Act: -0.0000

Data Index: 839646 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.4239. Min Act: -0.0000

Data Index: 1166802 (C4 (Web Text))

Max Activating Token Index: 964