Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1973 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.7549. Min Act: -0.1700
Data Index: 802728 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.7549. Min Act: -0.1700
Data Index: 516501 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6910. Min Act: -0.1700
Data Index: 842494 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6750. Min Act: -0.1700
Data Index: 1240189 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6910. Min Act: -0.1700
Data Index: 35819 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6750. Min Act: -0.1700
Data Index: 815727 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6429. Min Act: -0.1700
Data Index: 749790 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6589. Min Act: -0.1700
Data Index: 1337079 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6750. Min Act: -0.1700
Data Index: 158339 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6589. Min Act: -0.1700
Data Index: 988874 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6268. Min Act: -0.1700
Data Index: 1108186 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6268. Min Act: -0.1700
Data Index: 912280 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6108. Min Act: -0.1700
Data Index: 86642 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6429. Min Act: -0.1700
Data Index: 54161 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6268. Min Act: -0.1700
Data Index: 338951 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6108. Min Act: -0.1700
Data Index: 878626 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6108. Min Act: -0.1700
Data Index: 1177367 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6268. Min Act: -0.1700
Data Index: 795728 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.6268. Min Act: -0.1700
Data Index: 954897 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7549. Min Range: -2.7549
Max Act: 2.5786. Min Act: -0.1700
Data Index: 672895 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19