Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1062 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.1834. Min Range: -5.1834
Max Act: 5.1834. Min Act: -0.1700
Data Index: 171182 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1834. Min Range: -5.1834
Max Act: 5.0584. Min Act: -0.1700
Data Index: 760870 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1834. Min Range: -5.1834
Max Act: 5.0272. Min Act: -0.1700
Data Index: 702981 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9647. Min Act: -0.1700
Data Index: 457198 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9334. Min Act: -0.1700
Data Index: 1250287 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9334. Min Act: -0.1699
Data Index: 741353 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9334. Min Act: -0.1700
Data Index: 131894 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9334. Min Act: -0.1699
Data Index: 871451 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9334. Min Act: -0.1700
Data Index: 836658 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9022. Min Act: -0.1699
Data Index: 1219013 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8709. Min Act: -0.1700
Data Index: 266935 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9022. Min Act: -0.1700
Data Index: 1215858 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9022. Min Act: -0.1700
Data Index: 343633 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.9022. Min Act: -0.1700
Data Index: 602162 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8709. Min Act: -0.1700
Data Index: 295276 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1178395 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8709. Min Act: -0.1700
Data Index: 391794 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8397. Min Act: -0.1700
Data Index: 699031 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8397. Min Act: -0.1700
Data Index: 912821 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1834. Min Range: -5.1834
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1009718 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19