Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2009 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.6029. Min Act: -0.1700
Data Index: 896995 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.6190. Min Act: -0.1700
Data Index: 363289 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5868. Min Act: -0.1700
Data Index: 1413887 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.6029. Min Act: -0.1700
Data Index: 921344 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5707. Min Act: -0.1700
Data Index: 942428 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 1427491 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 505805 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 1612844 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 650288 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 221812 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 632339 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5223. Min Act: -0.1700
Data Index: 1218186 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5385. Min Act: -0.1700
Data Index: 1364386 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5385. Min Act: -0.1700
Data Index: 1614080 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5385. Min Act: -0.1700
Data Index: 1654439 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 1566272 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5546. Min Act: -0.1700
Data Index: 337738 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5385. Min Act: -0.1700
Data Index: 503623 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5385. Min Act: -0.1700
Data Index: 1090071 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6190. Min Range: -2.6190
Max Act: 2.5385. Min Act: -0.1700
Data Index: 1439620 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19