Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1337 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.5569. Min Act: -0.1700
Data Index: 49250 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.5084. Min Act: -0.1700
Data Index: 857687 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.5084. Min Act: -0.1700
Data Index: 663417 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4922. Min Act: -0.1700
Data Index: 888311 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4922. Min Act: -0.1700
Data Index: 880737 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4760. Min Act: -0.1700
Data Index: 799122 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4597. Min Act: -0.1700
Data Index: 49796 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4435. Min Act: -0.1700
Data Index: 515263 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4435. Min Act: -0.1700
Data Index: 967321 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4597. Min Act: -0.1700
Data Index: 1275150 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4272. Min Act: -0.1700
Data Index: 1453639 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4272. Min Act: -0.1700
Data Index: 93158 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4435. Min Act: -0.1700
Data Index: 1304024 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4435. Min Act: -0.1700
Data Index: 677409 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4272. Min Act: -0.1700
Data Index: 1071634 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4272. Min Act: -0.1700
Data Index: 37491 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4435. Min Act: -0.1700
Data Index: 733214 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4109. Min Act: -0.1700
Data Index: 592402 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4272. Min Act: -0.1700
Data Index: 781046 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5569. Min Range: -2.5569
Max Act: 2.4272. Min Act: -0.1700
Data Index: 452180 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19