Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 65 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.6338. Min Act: -0.1700
Data Index: 1094435 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.5400. Min Act: -0.1700
Data Index: 459645 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.4775. Min Act: -0.1700
Data Index: 252751 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.4775. Min Act: -0.1700
Data Index: 487077 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.4150. Min Act: -0.1700
Data Index: 466965 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.4775. Min Act: -0.1700
Data Index: 816707 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.4150. Min Act: -0.1700
Data Index: 518671 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.3837. Min Act: -0.1700
Data Index: 33207 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.4150. Min Act: -0.1700
Data Index: 980622 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.3837. Min Act: -0.1700
Data Index: 1069328 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.3525. Min Act: -0.1700
Data Index: 8929 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.3525. Min Act: -0.1700
Data Index: 65207 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.3525. Min Act: -0.1700
Data Index: 370147 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.2587. Min Act: -0.1700
Data Index: 246786 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.2275. Min Act: -0.1700
Data Index: 486732 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.2275. Min Act: -0.1700
Data Index: 343734 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.2275. Min Act: -0.1700
Data Index: 1284866 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.1962. Min Act: -0.1700
Data Index: 897926 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.1337. Min Act: -0.1700
Data Index: 272921 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6338. Min Range: -4.6338
Max Act: 4.1337. Min Act: -0.1700
Data Index: 18378 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19