Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2721 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.5215. Min Act: -0.0001
Data Index: 798100 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.5134. Min Act: -0.0001
Data Index: 806778 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4663. Min Act: -0.0001
Data Index: 539448 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4513. Min Act: -0.0001
Data Index: 1306140 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4602. Min Act: -0.0001
Data Index: 34189 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4269. Min Act: -0.0001
Data Index: 264960 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4432. Min Act: -0.0001
Data Index: 1221553 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4571. Min Act: -0.0001
Data Index: 1261492 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4405. Min Act: -0.0001
Data Index: 953707 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4499. Min Act: -0.0001
Data Index: 555242 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4205. Min Act: -0.0001
Data Index: 1261111 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.3916. Min Act: -0.0001
Data Index: 832812 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4425. Min Act: -0.0001
Data Index: 862392 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4267. Min Act: -0.0001
Data Index: 763436 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4031. Min Act: -0.0001
Data Index: 929287 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.3890. Min Act: -0.0001
Data Index: 669461 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4075. Min Act: -0.0001
Data Index: 988486 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4164. Min Act: -0.0001
Data Index: 1096636 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4405. Min Act: -0.0001
Data Index: 344787 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5215. Min Range: -0.5215
Max Act: 0.4040. Min Act: -0.0001
Data Index: 1287453 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19