Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2041 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.5850. Min Act: -0.1700
Data Index: 285959 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.5225. Min Act: -0.1700
Data Index: 664946 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.4600. Min Act: -0.1700
Data Index: 753004 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.4288. Min Act: -0.1700
Data Index: 912787 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.4288. Min Act: -0.1700
Data Index: 1178395 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.3975. Min Act: -0.1700
Data Index: 889996 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2413. Min Act: -0.1700
Data Index: 730724 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2413. Min Act: -0.1700
Data Index: 466017 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.3350. Min Act: -0.1700
Data Index: 839624 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2100. Min Act: -0.1700
Data Index: 409022 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.3038. Min Act: -0.1700
Data Index: 1322902 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2100. Min Act: -0.1700
Data Index: 364116 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2413. Min Act: -0.1699
Data Index: 887759 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2725. Min Act: -0.1700
Data Index: 286647 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2413. Min Act: -0.1700
Data Index: 606981 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.3350. Min Act: -0.1700
Data Index: 32995 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.3038. Min Act: -0.1700
Data Index: 383242 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.1788. Min Act: -0.1700
Data Index: 251069 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1006870 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5850. Min Range: -6.5850
Max Act: 6.2100. Min Act: -0.1700
Data Index: 64718 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19