Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 210 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.4866. Min Act: -0.1700
Data Index: 905837 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.3928. Min Act: -0.1700
Data Index: 911106 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.3616. Min Act: -0.1700
Data Index: 462137 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.4241. Min Act: -0.1700
Data Index: 1316943 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.3928. Min Act: -0.1700
Data Index: 831550 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2678. Min Act: -0.1700
Data Index: 212234 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2678. Min Act: -0.1700
Data Index: 202007 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2053. Min Act: -0.1700
Data Index: 1233222 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2053. Min Act: -0.1700
Data Index: 893611 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1740. Min Act: -0.1700
Data Index: 669222 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2053. Min Act: -0.1700
Data Index: 75304 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1740. Min Act: -0.1700
Data Index: 393656 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2366. Min Act: -0.1700
Data Index: 917057 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1740. Min Act: -0.1700
Data Index: 1309335 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.2053. Min Act: -0.1700
Data Index: 368059 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1428. Min Act: -0.1700
Data Index: 350758 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1428. Min Act: -0.1700
Data Index: 1920 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1428. Min Act: -0.1700
Data Index: 667444 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1740. Min Act: -0.1700
Data Index: 408958 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4866. Min Range: -4.4866
Max Act: 4.1740. Min Act: -0.1700
Data Index: 336041 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19