Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4648 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.3305. Min Range: -4.3305
Max Act: 4.3305. Min Act: -0.0001
Data Index: 605251 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3305. Min Range: -4.3305
Max Act: 4.0166. Min Act: -0.0001
Data Index: 732627 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3305. Min Range: -4.3305
Max Act: 4.3142. Min Act: -0.0001
Data Index: 1251773 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.6044. Min Act: -0.0001
Data Index: 1185439 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3305. Min Range: -4.3305
Max Act: 4.0129. Min Act: -0.0001
Data Index: 530305 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.8546. Min Act: -0.0001
Data Index: 31900 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.8343. Min Act: -0.0001
Data Index: 333622 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.4648. Min Act: -0.0001
Data Index: 700581 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.7478. Min Act: -0.0001
Data Index: 655211 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.7694. Min Act: -0.0001
Data Index: 693551 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.8877. Min Act: -0.0001
Data Index: 235258 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.6861. Min Act: -0.0001
Data Index: 1007729 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.4029. Min Act: -0.0001
Data Index: 412087 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.7021. Min Act: -0.0001
Data Index: 1304812 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.8397. Min Act: -0.0001
Data Index: 1306657 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.6552. Min Act: -0.0001
Data Index: 863700 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.3459. Min Act: -0.0001
Data Index: 1019286 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.6226. Min Act: -0.0001
Data Index: 200840 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.7579. Min Act: -0.0001
Data Index: 980823 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3305. Min Range: -4.3305
Max Act: 3.7586. Min Act: -0.0001
Data Index: 492495 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19