Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1303 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0586. Min Range: -6.0586
Max Act: 6.0586. Min Act: -0.1700
Data Index: 587015 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9336. Min Act: -0.1700
Data Index: 1333917 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9961. Min Act: -0.1700
Data Index: 197750 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9024. Min Act: -0.1700
Data Index: 142157 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9961. Min Act: -0.1700
Data Index: 453862 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9024. Min Act: -0.1700
Data Index: 131809 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9024. Min Act: -0.1700
Data Index: 860795 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.9024. Min Act: -0.1700
Data Index: 749248 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.8399. Min Act: -0.1700
Data Index: 1347198 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7461. Min Act: -0.1700
Data Index: 586232 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.8399. Min Act: -0.1700
Data Index: 1341914 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.8711. Min Act: -0.1700
Data Index: 1194087 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7774. Min Act: -0.1700
Data Index: 325333 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.8399. Min Act: -0.1700
Data Index: 648564 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.8086. Min Act: -0.1700
Data Index: 321797 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7461. Min Act: -0.1700
Data Index: 757304 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7774. Min Act: -0.1700
Data Index: 766671 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7461. Min Act: -0.1700
Data Index: 611054 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7461. Min Act: -0.1700
Data Index: 447610 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0586. Min Range: -6.0586
Max Act: 5.7149. Min Act: -0.1700
Data Index: 83018 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19