Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1817 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.5107. Min Act: -0.1700
Data Index: 1504450 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4783. Min Act: -0.1700
Data Index: 1635283 (Python Code)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4783. Min Act: -0.1700
Data Index: 1383746 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4621. Min Act: -0.1700
Data Index: 1621307 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4296. Min Act: -0.1700
Data Index: 105421 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4133. Min Act: -0.1700
Data Index: 1409816 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4296. Min Act: -0.1700
Data Index: 1015866 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4296. Min Act: -0.1700
Data Index: 980598 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4133. Min Act: -0.1700
Data Index: 1583138 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4133. Min Act: -0.1700
Data Index: 73108 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4133. Min Act: -0.1700
Data Index: 237706 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4133. Min Act: -0.1700
Data Index: 1307424 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.4133. Min Act: -0.1700
Data Index: 465113 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3970. Min Act: -0.1700
Data Index: 1639040 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3970. Min Act: -0.1700
Data Index: 1595630 (Python Code)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3970. Min Act: -0.1700
Data Index: 1540822 (Python Code)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3970. Min Act: -0.1700
Data Index: 802375 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3807. Min Act: -0.1700
Data Index: 1595820 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3643. Min Act: -0.1700
Data Index: 951938 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5107. Min Range: -2.5107
Max Act: 2.3643. Min Act: -0.1700
Data Index: 629999 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19