Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1074 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.6729. Min Act: -0.1700
Data Index: 1594078 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.6248. Min Act: -0.1700
Data Index: 1521933 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.6408. Min Act: -0.1700
Data Index: 1382615 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5926. Min Act: -0.1700
Data Index: 1551228 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.6087. Min Act: -0.1700
Data Index: 1622405 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5765. Min Act: -0.1700
Data Index: 1390181 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5765. Min Act: -0.1700
Data Index: 1512593 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5604. Min Act: -0.1700
Data Index: 1562341 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5604. Min Act: -0.1700
Data Index: 1375942 (Python Code)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5442. Min Act: -0.1700
Data Index: 1560623 (Python Code)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5281. Min Act: -0.1700
Data Index: 1456686 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5442. Min Act: -0.1700
Data Index: 1517630 (Python Code)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5281. Min Act: -0.1700
Data Index: 1424646 (Python Code)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5442. Min Act: -0.1700
Data Index: 1617093 (Python Code)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5281. Min Act: -0.1700
Data Index: 1582746 (Python Code)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5281. Min Act: -0.1700
Data Index: 231559 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.4957. Min Act: -0.1700
Data Index: 447579 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5119. Min Act: -0.1700
Data Index: 1450549 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5119. Min Act: -0.1700
Data Index: 1578439 (Python Code)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6729. Min Range: -2.6729
Max Act: 2.5119. Min Act: -0.1700
Data Index: 1507297 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19