Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 296 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.1326. Min Range: -6.1326
Max Act: 6.1326. Min Act: -0.1700
Data Index: 1087884 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.7889. Min Act: -0.1699
Data Index: 1077261 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.6639. Min Act: -0.1700
Data Index: 734513 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.6639. Min Act: -0.1700
Data Index: 519802 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.5701. Min Act: -0.1700
Data Index: 825627 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.6014. Min Act: -0.1700
Data Index: 307635 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.5076. Min Act: -0.1700
Data Index: 1133159 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.5076. Min Act: -0.1700
Data Index: 716945 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.4764. Min Act: -0.1700
Data Index: 109991 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.4451. Min Act: -0.1700
Data Index: 1199601 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.4451. Min Act: -0.1700
Data Index: 3534 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.3826. Min Act: -0.1700
Data Index: 1339787 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.4451. Min Act: -0.1700
Data Index: 190439 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.4139. Min Act: -0.1700
Data Index: 684722 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.3826. Min Act: -0.1700
Data Index: 1151889 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.3201. Min Act: -0.1700
Data Index: 995746 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.3826. Min Act: -0.1700
Data Index: 1194281 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.3201. Min Act: -0.1700
Data Index: 1356121 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.2889. Min Act: -0.1700
Data Index: 48127 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1326. Min Range: -6.1326
Max Act: 5.3514. Min Act: -0.1700
Data Index: 970880 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19