Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1987 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0060. Min Range: -2.0060
Max Act: 2.0060. Min Act: -0.0001
Data Index: 1554483 (Python Code)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.8359. Min Act: -0.0001
Data Index: 1291758 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.7093. Min Act: -0.0001
Data Index: 1088013 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.6883. Min Act: -0.0001
Data Index: 433922 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.5520. Min Act: -0.0001
Data Index: 1256655 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.6438. Min Act: -0.0001
Data Index: 177895 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.7461. Min Act: -0.0001
Data Index: 759550 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.5752. Min Act: -0.0001
Data Index: 1089865 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.5302. Min Act: -0.0001
Data Index: 495077 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.5069. Min Act: -0.0001
Data Index: 130673 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4976. Min Act: -0.0001
Data Index: 9497 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4838. Min Act: -0.0001
Data Index: 861135 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4944. Min Act: -0.0001
Data Index: 1332272 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.5608. Min Act: -0.0001
Data Index: 374868 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.3468. Min Act: -0.0001
Data Index: 361571 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4008. Min Act: -0.0001
Data Index: 1021048 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4130. Min Act: -0.0001
Data Index: 1565720 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.3960. Min Act: -0.0001
Data Index: 60062 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4731. Min Act: -0.0001
Data Index: 268742 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0060. Min Range: -2.0060
Max Act: 1.4700. Min Act: -0.0001
Data Index: 1267838 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19