Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2022 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.7691. Min Act: -0.1700
Data Index: 1029459 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.6129. Min Act: -0.1700
Data Index: 1490607 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.5191. Min Act: -0.1700
Data Index: 980979 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.5504. Min Act: -0.1700
Data Index: 1199538 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4566. Min Act: -0.1700
Data Index: 1277456 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4879. Min Act: -0.1700
Data Index: 1400726 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4566. Min Act: -0.1700
Data Index: 1002553 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4879. Min Act: -0.1700
Data Index: 818929 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4254. Min Act: -0.1700
Data Index: 881140 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4254. Min Act: -0.1700
Data Index: 905803 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4254. Min Act: -0.1700
Data Index: 877813 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3941. Min Act: -0.1700
Data Index: 1580873 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3316. Min Act: -0.1700
Data Index: 1442796 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.4254. Min Act: -0.1700
Data Index: 379054 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3629. Min Act: -0.1700
Data Index: 278339 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3941. Min Act: -0.1700
Data Index: 1605852 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3629. Min Act: -0.1700
Data Index: 1368978 (Python Code)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3941. Min Act: -0.1700
Data Index: 326285 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.3316. Min Act: -0.1700
Data Index: 1592140 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7691. Min Range: -4.7691
Max Act: 4.2691. Min Act: -0.1700
Data Index: 1593373 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19