Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 786 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.1553. Min Act: -0.1700
Data Index: 550826 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.1240. Min Act: -0.1700
Data Index: 972746 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.0615. Min Act: -0.1700
Data Index: 641842 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.1240. Min Act: -0.1700
Data Index: 204287 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.0615. Min Act: -0.1700
Data Index: 662229 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9990. Min Act: -0.1700
Data Index: 661890 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9990. Min Act: -0.1700
Data Index: 994947 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9990. Min Act: -0.1700
Data Index: 164606 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.0303. Min Act: -0.1700
Data Index: 1287173 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9678. Min Act: -0.1700
Data Index: 712217 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.0615. Min Act: -0.1700
Data Index: 1254373 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9990. Min Act: -0.1700
Data Index: 1107708 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9990. Min Act: -0.1700
Data Index: 241704 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9678. Min Act: -0.1700
Data Index: 82161 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9678. Min Act: -0.1700
Data Index: 1048750 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1553. Min Range: -6.1553
Max Act: 6.0303. Min Act: -0.1700
Data Index: 93760 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9678. Min Act: -0.1700
Data Index: 1108646 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9678. Min Act: -0.1700
Data Index: 884058 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9053. Min Act: -0.1700
Data Index: 947953 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1553. Min Range: -6.1553
Max Act: 5.9365. Min Act: -0.1700
Data Index: 547510 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19