Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 930 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1941. Min Act: -0.1700
Data Index: 1299511 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1941. Min Act: -0.1700
Data Index: 1133395 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.2879. Min Act: -0.1700
Data Index: 468955 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.2254. Min Act: -0.1700
Data Index: 464313 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1941. Min Act: -0.1700
Data Index: 1213210 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1941. Min Act: -0.1700
Data Index: 800403 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1941. Min Act: -0.1700
Data Index: 575977 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.2254. Min Act: -0.1700
Data Index: 1348407 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1629. Min Act: -0.1700
Data Index: 679797 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1629. Min Act: -0.1700
Data Index: 844175 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1316. Min Act: -0.1700
Data Index: 108564 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1004. Min Act: -0.1699
Data Index: 106174 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1004. Min Act: -0.1700
Data Index: 855920 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1316. Min Act: -0.1700
Data Index: 196829 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1004. Min Act: -0.1700
Data Index: 121510 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1316. Min Act: -0.1700
Data Index: 598444 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1004. Min Act: -0.1700
Data Index: 1128222 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.1004. Min Act: -0.1700
Data Index: 582876 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.0691. Min Act: -0.1700
Data Index: 991634 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2879. Min Range: -4.2879
Max Act: 4.0691. Min Act: -0.1700
Data Index: 1132865 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19