Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1936 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.7363. Min Act: -0.1700
Data Index: 135940 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.6737. Min Act: -0.1700
Data Index: 763436 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.6737. Min Act: -0.1700
Data Index: 1234087 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.6737. Min Act: -0.1700
Data Index: 1094351 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.6424. Min Act: -0.1700
Data Index: 554842 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.6111. Min Act: -0.1700
Data Index: 1282405 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5485. Min Act: -0.1700
Data Index: 57356 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5798. Min Act: -0.1700
Data Index: 742709 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5798. Min Act: -0.1700
Data Index: 321201 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5798. Min Act: -0.1700
Data Index: 1186243 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5171. Min Act: -0.1700
Data Index: 125895 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5798. Min Act: -0.1700
Data Index: 92949 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5485. Min Act: -0.1700
Data Index: 361479 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5171. Min Act: -0.1700
Data Index: 1348297 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5485. Min Act: -0.1700
Data Index: 500620 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5485. Min Act: -0.1700
Data Index: 409753 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5798. Min Act: -0.1700
Data Index: 1065873 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5485. Min Act: -0.1700
Data Index: 1345625 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5485. Min Act: -0.1700
Data Index: 1325683 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7363. Min Range: -3.7363
Max Act: 3.5171. Min Act: -0.1700
Data Index: 1176096 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19