Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 968 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1710. Min Range: -3.1710
Max Act: 3.1710. Min Act: -0.1700
Data Index: 1579061 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1710. Min Range: -3.1710
Max Act: 3.1553. Min Act: -0.1700
Data Index: 1582104 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1710. Min Range: -3.1710
Max Act: 3.1080. Min Act: -0.1700
Data Index: 1606254 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1710. Min Range: -3.1710
Max Act: 3.0607. Min Act: -0.1700
Data Index: 862961 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1710. Min Range: -3.1710
Max Act: 3.0133. Min Act: -0.1700
Data Index: 320709 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1710. Min Range: -3.1710
Max Act: 3.0291. Min Act: -0.1700
Data Index: 711230 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9500. Min Act: -0.1700
Data Index: 807555 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9183. Min Act: -0.1700
Data Index: 1606725 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9342. Min Act: -0.1700
Data Index: 61955 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9025. Min Act: -0.1700
Data Index: 1568727 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9183. Min Act: -0.1700
Data Index: 587026 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9025. Min Act: -0.1700
Data Index: 1539477 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8866. Min Act: -0.1700
Data Index: 1472611 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8708. Min Act: -0.1700
Data Index: 142710 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8708. Min Act: -0.1700
Data Index: 1380181 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8866. Min Act: -0.1700
Data Index: 1603869 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8866. Min Act: -0.1700
Data Index: 1294997 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8866. Min Act: -0.1700
Data Index: 1479210 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.9025. Min Act: -0.1700
Data Index: 270270 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1710. Min Range: -3.1710
Max Act: 2.8549. Min Act: -0.1700
Data Index: 332011 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19