Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4073 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5747. Min Act: -0.0001
Data Index: 1154891 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4517. Min Act: -0.0001
Data Index: 901097 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4874. Min Act: -0.0001
Data Index: 577560 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4133. Min Act: -0.0001
Data Index: 1244581 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3806. Min Act: -0.0001
Data Index: 693314 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3775. Min Act: -0.0001
Data Index: 858646 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2956. Min Act: -0.0001
Data Index: 269124 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3640. Min Act: -0.0001
Data Index: 95514 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3683. Min Act: -0.0001
Data Index: 1315411 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3672. Min Act: -0.0001
Data Index: 883796 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2787. Min Act: -0.0001
Data Index: 619313 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3000. Min Act: -0.0001
Data Index: 1274349 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2957. Min Act: -0.0001
Data Index: 1162633 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2644. Min Act: -0.0001
Data Index: 105008 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2958. Min Act: -0.0001
Data Index: 281948 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.1736. Min Act: -0.0001
Data Index: 1321196 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4905. Min Act: -0.0001
Data Index: 478314 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2488. Min Act: -0.0001
Data Index: 1160562 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.2424. Min Act: -0.0001
Data Index: 165002 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3191. Min Act: -0.0001
Data Index: 80690 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19