Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1896 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.7373. Min Act: -0.1700
Data Index: 411394 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.7053. Min Act: -0.1700
Data Index: 981446 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.6412. Min Act: -0.1700
Data Index: 102438 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.6252. Min Act: -0.1700
Data Index: 648735 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5930. Min Act: -0.1700
Data Index: 1125859 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5769. Min Act: -0.1700
Data Index: 853240 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5930. Min Act: -0.1700
Data Index: 938090 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5769. Min Act: -0.1700
Data Index: 763736 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5769. Min Act: -0.1700
Data Index: 1255762 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5608. Min Act: -0.1700
Data Index: 1289772 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5446. Min Act: -0.1700
Data Index: 7297 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5446. Min Act: -0.1700
Data Index: 1320264 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5446. Min Act: -0.1700
Data Index: 889854 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5285. Min Act: -0.1700
Data Index: 1126640 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5608. Min Act: -0.1700
Data Index: 419034 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5285. Min Act: -0.1700
Data Index: 196030 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5285. Min Act: -0.1700
Data Index: 1274484 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5123. Min Act: -0.1700
Data Index: 595567 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.4961. Min Act: -0.1700
Data Index: 677135 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7373. Min Range: -2.7373
Max Act: 2.5123. Min Act: -0.1700
Data Index: 54199 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19