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

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

Neuron 4757 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.7976. Min Act: -0.0000

Data Index: 665443 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 4.1172. Min Range: -4.1172

Max Act: 4.1172. Min Act: -0.0000

Data Index: 208340 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.7474. Min Act: -0.0000

Data Index: 1104091 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.6118. Min Act: -0.0000

Data Index: 94521 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.4354. Min Act: -0.0000

Data Index: 330084 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.4197. Min Act: -0.0000

Data Index: 144916 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.6800. Min Act: -0.0000

Data Index: 1064802 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.4041. Min Act: -0.0000

Data Index: 801871 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.3031. Min Act: -0.0000

Data Index: 624627 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.4586. Min Act: -0.0000

Data Index: 687736 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.3327. Min Act: -0.0000

Data Index: 1051871 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.1510. Min Act: -0.0000

Data Index: 1518623 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.0090. Min Act: -0.0000

Data Index: 996153 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.1396. Min Act: -0.0000

Data Index: 1086390 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.1068. Min Act: -0.0000

Data Index: 239459 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.2475. Min Act: -0.0000

Data Index: 1457797 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.0633. Min Act: -0.0000

Data Index: 644153 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 4.1172. Min Range: -4.1172

Max Act: 2.8869. Min Act: -0.0000

Data Index: 457908 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 4.1172. Min Range: -4.1172

Max Act: 3.0287. Min Act: -0.0000

Data Index: 35502 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 4.1172. Min Range: -4.1172

Max Act: 2.9751. Min Act: -0.0000

Data Index: 87140 (C4 (Web Text))

Max Activating Token Index: 299