Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 547 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.7009. Min Act: -0.1700
Data Index: 141085 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6849. Min Act: -0.1700
Data Index: 576114 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6849. Min Act: -0.1699
Data Index: 1540501 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6689. Min Act: -0.1700
Data Index: 490925 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6528. Min Act: -0.1700
Data Index: 204165 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6528. Min Act: -0.1699
Data Index: 1491008 (Python Code)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 1643993 (Python Code)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6528. Min Act: -0.1700
Data Index: 1520137 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6528. Min Act: -0.1700
Data Index: 568939 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6689. Min Act: -0.1700
Data Index: 883649 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 1072155 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 312795 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6207. Min Act: -0.1700
Data Index: 1628704 (Python Code)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 1045364 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 367661 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 281581 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6207. Min Act: -0.1700
Data Index: 277647 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6368. Min Act: -0.1700
Data Index: 1173463 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6207. Min Act: -0.1700
Data Index: 468883 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7009. Min Range: -2.7009
Max Act: 2.6207. Min Act: -0.1700
Data Index: 748205 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19