Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3542 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.9364. Min Act: -0.0001
Data Index: 575864 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0525. Min Range: -2.0525
Max Act: 2.0525. Min Act: -0.0002
Data Index: 989960 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.9616. Min Act: -0.0002
Data Index: 333786 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.8688. Min Act: -0.0001
Data Index: 312044 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.9680. Min Act: -0.0001
Data Index: 1055524 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.8544. Min Act: -0.0001
Data Index: 311946 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.6054. Min Act: -0.0001
Data Index: 1147865 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4741. Min Act: -0.0001
Data Index: 216782 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.6310. Min Act: -0.0001
Data Index: 335988 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.7911. Min Act: -0.0001
Data Index: 142185 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4995. Min Act: -0.0001
Data Index: 1276187 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.5085. Min Act: -0.0001
Data Index: 132752 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4124. Min Act: -0.0001
Data Index: 262655 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.5915. Min Act: -0.0002
Data Index: 1109440 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4496. Min Act: -0.0001
Data Index: 611434 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4960. Min Act: -0.0001
Data Index: 311111 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.5228. Min Act: -0.0001
Data Index: 1128903 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4428. Min Act: -0.0001
Data Index: 710901 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.5092. Min Act: -0.0001
Data Index: 892340 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0525. Min Range: -2.0525
Max Act: 1.4315. Min Act: -0.0001
Data Index: 804011 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19