Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3141 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.3844. Min Act: -0.0001
Data Index: 1543236 (Python Code)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.0493. Min Act: -0.0001
Data Index: 1377263 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.0389. Min Act: -0.0001
Data Index: 1422834 (Python Code)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3844. Min Range: -2.3844
Max Act: 2.0586. Min Act: -0.0001
Data Index: 1432192 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.6818. Min Act: -0.0000
Data Index: 953752 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.9294. Min Act: -0.0000
Data Index: 1290441 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8798. Min Act: -0.0001
Data Index: 1594871 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8101. Min Act: -0.0001
Data Index: 1376131 (Python Code)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8058. Min Act: -0.0001
Data Index: 1521874 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8385. Min Act: -0.0001
Data Index: 1564250 (Python Code)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8466. Min Act: -0.0001
Data Index: 1630648 (Python Code)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8761. Min Act: -0.0001
Data Index: 1406721 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8305. Min Act: -0.0001
Data Index: 1414713 (Python Code)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.8618. Min Act: -0.0001
Data Index: 1639228 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.7808. Min Act: -0.0001
Data Index: 1397031 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.7671. Min Act: -0.0001
Data Index: 1559140 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.7587. Min Act: -0.0001
Data Index: 1559135 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.7925. Min Act: -0.0001
Data Index: 1405212 (Python Code)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.7393. Min Act: -0.0001
Data Index: 1365760 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3844. Min Range: -2.3844
Max Act: 1.6662. Min Act: -0.0001
Data Index: 1653918 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19