Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1968 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.3804. Min Act: -0.1700
Data Index: 1254320 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.2867. Min Act: -0.1700
Data Index: 576702 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1929. Min Act: -0.1700
Data Index: 1337360 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1929. Min Act: -0.1700
Data Index: 1240702 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 277036 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1616. Min Act: -0.1700
Data Index: 933286 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 229691 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.0991. Min Act: -0.1700
Data Index: 224259 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1929. Min Act: -0.1700
Data Index: 465379 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 315391 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.0991. Min Act: -0.1700
Data Index: 299615 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 1101441 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 120488 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 909226 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.0991. Min Act: -0.1700
Data Index: 227776 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.0991. Min Act: -0.1700
Data Index: 355207 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.0991. Min Act: -0.1700
Data Index: 1264007 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 32260 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1929. Min Act: -0.1700
Data Index: 7834 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3804. Min Range: -4.3804
Max Act: 4.1304. Min Act: -0.1700
Data Index: 1293569 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19