Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1536 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0304. Min Range: -5.0304
Max Act: 5.0304. Min Act: -0.1700
Data Index: 708613 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.9991. Min Act: -0.1700
Data Index: 854514 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1019081 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8741. Min Act: -0.1700
Data Index: 500918 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.9210. Min Act: -0.1700
Data Index: 117907 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8897. Min Act: -0.1700
Data Index: 614490 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8585. Min Act: -0.1700
Data Index: 1054200 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8272. Min Act: -0.1700
Data Index: 538772 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8272. Min Act: -0.1700
Data Index: 291282 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7960. Min Act: -0.1700
Data Index: 261688 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7960. Min Act: -0.1700
Data Index: 1312315 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7335. Min Act: -0.1700
Data Index: 721905 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8116. Min Act: -0.1700
Data Index: 1149374 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.8116. Min Act: -0.1700
Data Index: 1072841 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7960. Min Act: -0.1700
Data Index: 1274349 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7804. Min Act: -0.1700
Data Index: 578846 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7491. Min Act: -0.1700
Data Index: 1284953 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7179. Min Act: -0.1700
Data Index: 841360 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7335. Min Act: -0.1700
Data Index: 1160562 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0304. Min Range: -5.0304
Max Act: 4.7335. Min Act: -0.1700
Data Index: 1244581 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19