Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4092 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6782. Min Act: -0.0001
Data Index: 229152 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6711. Min Act: -0.0001
Data Index: 122985 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6632. Min Act: -0.0001
Data Index: 1160773 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6791. Min Act: -0.0001
Data Index: 884864 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6811. Min Act: -0.0001
Data Index: 767454 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5828. Min Act: -0.0001
Data Index: 780801 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5728. Min Act: -0.0001
Data Index: 1273905 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6537. Min Act: -0.0001
Data Index: 1020440 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5810. Min Act: -0.0001
Data Index: 1002459 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6211. Min Act: -0.0001
Data Index: 93801 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5985. Min Act: -0.0001
Data Index: 1097004 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6118. Min Act: -0.0002
Data Index: 281496 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6023. Min Act: -0.0001
Data Index: 733583 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5793. Min Act: -0.0001
Data Index: 547686 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5447. Min Act: -0.0001
Data Index: 776938 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5537. Min Act: -0.0001
Data Index: 601198 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5712. Min Act: -0.0001
Data Index: 417169 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5886. Min Act: -0.0001
Data Index: 1081097 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.5876. Min Act: -0.0001
Data Index: 336457 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6811. Min Range: -0.6811
Max Act: 0.6059. Min Act: -0.0001
Data Index: 1251201 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19