Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4014 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.4782. Min Range: -4.4782
Max Act: 4.4782. Min Act: -0.0001
Data Index: 308376 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.3047. Min Act: -0.0001
Data Index: 730774 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.5944. Min Act: -0.0001
Data Index: 301037 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.6698. Min Act: -0.0001
Data Index: 1228369 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.4597. Min Act: -0.0001
Data Index: 814824 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.2296. Min Act: -0.0001
Data Index: 1063836 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.4469. Min Act: -0.0001
Data Index: 634455 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.0951. Min Act: -0.0001
Data Index: 126053 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.7643. Min Act: -0.0001
Data Index: 848984 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.8901. Min Act: -0.0001
Data Index: 415362 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.1004. Min Act: -0.0001
Data Index: 386605 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.9952. Min Act: -0.0001
Data Index: 658459 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.0519. Min Act: -0.0001
Data Index: 1249731 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.7743. Min Act: -0.0001
Data Index: 816036 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.8914. Min Act: -0.0001
Data Index: 186350 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.8640. Min Act: -0.0001
Data Index: 637420 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4782. Min Range: -4.4782
Max Act: 3.1507. Min Act: -0.0001
Data Index: 1142415 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.8825. Min Act: -0.0001
Data Index: 648473 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.7525. Min Act: -0.0001
Data Index: 1043944 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4782. Min Range: -4.4782
Max Act: 2.7105. Min Act: -0.0001
Data Index: 1047908 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19